[2024-12-28 00:48:49,042][01536] Saving configuration to /content/train_dir/default_experiment/config.json... [2024-12-28 00:48:49,055][01536] Rollout worker 0 uses device cpu [2024-12-28 00:48:49,056][01536] Rollout worker 1 uses device cpu [2024-12-28 00:48:49,059][01536] Rollout worker 2 uses device cpu [2024-12-28 00:48:49,062][01536] Rollout worker 3 uses device cpu [2024-12-28 00:48:49,066][01536] Rollout worker 4 uses device cpu [2024-12-28 00:48:49,070][01536] Rollout worker 5 uses device cpu [2024-12-28 00:48:49,073][01536] Rollout worker 6 uses device cpu [2024-12-28 00:48:49,077][01536] Rollout worker 7 uses device cpu [2024-12-28 00:48:49,354][01536] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-12-28 00:48:49,357][01536] InferenceWorker_p0-w0: min num requests: 2 [2024-12-28 00:48:49,427][01536] Starting all processes... [2024-12-28 00:48:49,443][01536] Starting process learner_proc0 [2024-12-28 00:48:49,570][01536] Starting all processes... [2024-12-28 00:48:49,616][01536] Starting process inference_proc0-0 [2024-12-28 00:48:49,617][01536] Starting process rollout_proc0 [2024-12-28 00:48:49,617][01536] Starting process rollout_proc1 [2024-12-28 00:48:49,624][01536] Starting process rollout_proc2 [2024-12-28 00:48:49,652][01536] Starting process rollout_proc3 [2024-12-28 00:48:49,652][01536] Starting process rollout_proc4 [2024-12-28 00:48:49,653][01536] Starting process rollout_proc5 [2024-12-28 00:48:49,653][01536] Starting process rollout_proc6 [2024-12-28 00:48:49,653][01536] Starting process rollout_proc7 [2024-12-28 00:49:07,042][03573] Worker 0 uses CPU cores [0] [2024-12-28 00:49:07,494][03555] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-12-28 00:49:07,497][03555] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2024-12-28 00:49:07,551][03555] Num visible devices: 1 [2024-12-28 00:49:07,585][03555] Starting seed is not provided [2024-12-28 00:49:07,586][03555] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-12-28 00:49:07,587][03555] Initializing actor-critic model on device cuda:0 [2024-12-28 00:49:07,588][03555] RunningMeanStd input shape: (3, 72, 128) [2024-12-28 00:49:07,591][03555] RunningMeanStd input shape: (1,) [2024-12-28 00:49:07,654][03555] ConvEncoder: input_channels=3 [2024-12-28 00:49:07,688][03577] Worker 4 uses CPU cores [0] [2024-12-28 00:49:07,718][03580] Worker 7 uses CPU cores [1] [2024-12-28 00:49:07,733][03576] Worker 3 uses CPU cores [1] [2024-12-28 00:49:07,752][03578] Worker 6 uses CPU cores [0] [2024-12-28 00:49:07,789][03575] Worker 2 uses CPU cores [0] [2024-12-28 00:49:07,879][03579] Worker 5 uses CPU cores [1] [2024-12-28 00:49:07,884][03574] Worker 1 uses CPU cores [1] [2024-12-28 00:49:07,970][03572] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-12-28 00:49:07,970][03572] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2024-12-28 00:49:07,991][03572] Num visible devices: 1 [2024-12-28 00:49:08,040][03555] Conv encoder output size: 512 [2024-12-28 00:49:08,040][03555] Policy head output size: 512 [2024-12-28 00:49:08,095][03555] Created Actor Critic model with architecture: [2024-12-28 00:49:08,095][03555] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2024-12-28 00:49:08,493][03555] Using optimizer [2024-12-28 00:49:09,327][01536] Heartbeat connected on Batcher_0 [2024-12-28 00:49:09,355][01536] Heartbeat connected on InferenceWorker_p0-w0 [2024-12-28 00:49:09,384][01536] Heartbeat connected on RolloutWorker_w0 [2024-12-28 00:49:09,389][01536] Heartbeat connected on RolloutWorker_w1 [2024-12-28 00:49:09,394][01536] Heartbeat connected on RolloutWorker_w2 [2024-12-28 00:49:09,403][01536] Heartbeat connected on RolloutWorker_w3 [2024-12-28 00:49:09,405][01536] Heartbeat connected on RolloutWorker_w4 [2024-12-28 00:49:09,412][01536] Heartbeat connected on RolloutWorker_w5 [2024-12-28 00:49:09,419][01536] Heartbeat connected on RolloutWorker_w6 [2024-12-28 00:49:09,424][01536] Heartbeat connected on RolloutWorker_w7 [2024-12-28 00:49:12,517][03555] No checkpoints found [2024-12-28 00:49:12,518][03555] Did not load from checkpoint, starting from scratch! [2024-12-28 00:49:12,518][03555] Initialized policy 0 weights for model version 0 [2024-12-28 00:49:12,528][03555] LearnerWorker_p0 finished initialization! [2024-12-28 00:49:12,529][03555] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-12-28 00:49:12,532][01536] Heartbeat connected on LearnerWorker_p0 [2024-12-28 00:49:12,761][03572] RunningMeanStd input shape: (3, 72, 128) [2024-12-28 00:49:12,763][03572] RunningMeanStd input shape: (1,) [2024-12-28 00:49:12,783][03572] ConvEncoder: input_channels=3 [2024-12-28 00:49:12,948][03572] Conv encoder output size: 512 [2024-12-28 00:49:12,949][03572] Policy head output size: 512 [2024-12-28 00:49:13,026][01536] Inference worker 0-0 is ready! [2024-12-28 00:49:13,028][01536] All inference workers are ready! Signal rollout workers to start! [2024-12-28 00:49:13,262][03577] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,264][03578] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,266][03573] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,271][03575] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,355][03574] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,352][03579] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,359][03580] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:13,364][03576] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 00:49:14,564][03574] Decorrelating experience for 0 frames... [2024-12-28 00:49:14,566][03579] Decorrelating experience for 0 frames... [2024-12-28 00:49:14,924][03577] Decorrelating experience for 0 frames... [2024-12-28 00:49:14,926][03573] Decorrelating experience for 0 frames... [2024-12-28 00:49:14,933][03578] Decorrelating experience for 0 frames... [2024-12-28 00:49:14,963][01536] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-12-28 00:49:16,006][03576] Decorrelating experience for 0 frames... [2024-12-28 00:49:16,055][03579] Decorrelating experience for 32 frames... [2024-12-28 00:49:16,062][03574] Decorrelating experience for 32 frames... [2024-12-28 00:49:16,133][03580] Decorrelating experience for 0 frames... [2024-12-28 00:49:16,407][03577] Decorrelating experience for 32 frames... [2024-12-28 00:49:16,410][03573] Decorrelating experience for 32 frames... [2024-12-28 00:49:16,412][03578] Decorrelating experience for 32 frames... [2024-12-28 00:49:16,416][03575] Decorrelating experience for 0 frames... [2024-12-28 00:49:17,483][03580] Decorrelating experience for 32 frames... [2024-12-28 00:49:17,494][03573] Decorrelating experience for 64 frames... [2024-12-28 00:49:17,497][03577] Decorrelating experience for 64 frames... [2024-12-28 00:49:17,859][03579] Decorrelating experience for 64 frames... [2024-12-28 00:49:17,957][03576] Decorrelating experience for 32 frames... [2024-12-28 00:49:17,967][03574] Decorrelating experience for 64 frames... [2024-12-28 00:49:18,900][03579] Decorrelating experience for 96 frames... [2024-12-28 00:49:18,933][03575] Decorrelating experience for 32 frames... [2024-12-28 00:49:18,959][03574] Decorrelating experience for 96 frames... [2024-12-28 00:49:19,026][03573] Decorrelating experience for 96 frames... [2024-12-28 00:49:19,041][03577] Decorrelating experience for 96 frames... [2024-12-28 00:49:19,444][03578] Decorrelating experience for 64 frames... [2024-12-28 00:49:19,831][03575] Decorrelating experience for 64 frames... [2024-12-28 00:49:19,963][01536] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-12-28 00:49:20,181][03576] Decorrelating experience for 64 frames... [2024-12-28 00:49:20,256][03580] Decorrelating experience for 64 frames... [2024-12-28 00:49:20,748][03580] Decorrelating experience for 96 frames... [2024-12-28 00:49:20,867][03578] Decorrelating experience for 96 frames... [2024-12-28 00:49:21,063][03575] Decorrelating experience for 96 frames... [2024-12-28 00:49:22,317][03576] Decorrelating experience for 96 frames... [2024-12-28 00:49:24,963][01536] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 61.8. Samples: 618. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-12-28 00:49:24,966][01536] Avg episode reward: [(0, '1.892')] [2024-12-28 00:49:25,178][03555] Signal inference workers to stop experience collection... [2024-12-28 00:49:25,194][03572] InferenceWorker_p0-w0: stopping experience collection [2024-12-28 00:49:29,005][03555] Signal inference workers to resume experience collection... [2024-12-28 00:49:29,007][03572] InferenceWorker_p0-w0: resuming experience collection [2024-12-28 00:49:29,963][01536] Fps is (10 sec: 819.2, 60 sec: 546.1, 300 sec: 546.1). Total num frames: 8192. Throughput: 0: 180.5. Samples: 2708. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2024-12-28 00:49:29,969][01536] Avg episode reward: [(0, '2.520')] [2024-12-28 00:49:34,963][01536] Fps is (10 sec: 3276.9, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 32768. Throughput: 0: 409.3. Samples: 8186. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:49:34,968][01536] Avg episode reward: [(0, '3.771')] [2024-12-28 00:49:36,200][03572] Updated weights for policy 0, policy_version 10 (0.0156) [2024-12-28 00:49:39,963][01536] Fps is (10 sec: 4505.7, 60 sec: 2129.9, 300 sec: 2129.9). Total num frames: 53248. Throughput: 0: 469.7. Samples: 11742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:49:39,970][01536] Avg episode reward: [(0, '4.491')] [2024-12-28 00:49:44,965][01536] Fps is (10 sec: 3685.7, 60 sec: 2320.9, 300 sec: 2320.9). Total num frames: 69632. Throughput: 0: 560.6. Samples: 16818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:49:44,973][01536] Avg episode reward: [(0, '4.475')] [2024-12-28 00:49:47,603][03572] Updated weights for policy 0, policy_version 20 (0.0039) [2024-12-28 00:49:49,963][01536] Fps is (10 sec: 3686.4, 60 sec: 2574.6, 300 sec: 2574.6). Total num frames: 90112. Throughput: 0: 649.6. Samples: 22736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:49:49,970][01536] Avg episode reward: [(0, '4.443')] [2024-12-28 00:49:54,963][01536] Fps is (10 sec: 4506.4, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 114688. Throughput: 0: 655.4. Samples: 26214. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:49:54,965][01536] Avg episode reward: [(0, '4.341')] [2024-12-28 00:49:54,971][03555] Saving new best policy, reward=4.341! [2024-12-28 00:49:56,917][03572] Updated weights for policy 0, policy_version 30 (0.0024) [2024-12-28 00:49:59,963][01536] Fps is (10 sec: 4096.0, 60 sec: 2912.7, 300 sec: 2912.7). Total num frames: 131072. Throughput: 0: 711.9. Samples: 32034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:49:59,966][01536] Avg episode reward: [(0, '4.333')] [2024-12-28 00:50:04,963][01536] Fps is (10 sec: 3276.8, 60 sec: 2949.1, 300 sec: 2949.1). Total num frames: 147456. Throughput: 0: 823.0. Samples: 37034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:50:04,966][01536] Avg episode reward: [(0, '4.427')] [2024-12-28 00:50:04,973][03555] Saving new best policy, reward=4.427! [2024-12-28 00:50:07,828][03572] Updated weights for policy 0, policy_version 40 (0.0034) [2024-12-28 00:50:09,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3127.9, 300 sec: 3127.9). Total num frames: 172032. Throughput: 0: 886.0. Samples: 40488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:50:09,966][01536] Avg episode reward: [(0, '4.403')] [2024-12-28 00:50:14,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3208.5, 300 sec: 3208.5). Total num frames: 192512. Throughput: 0: 994.2. Samples: 47446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:50:14,970][01536] Avg episode reward: [(0, '4.255')] [2024-12-28 00:50:19,244][03572] Updated weights for policy 0, policy_version 50 (0.0020) [2024-12-28 00:50:19,963][01536] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3150.8). Total num frames: 204800. Throughput: 0: 967.1. Samples: 51704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:50:19,967][01536] Avg episode reward: [(0, '4.313')] [2024-12-28 00:50:24,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 229376. Throughput: 0: 961.4. Samples: 55004. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:50:24,970][01536] Avg episode reward: [(0, '4.312')] [2024-12-28 00:50:28,314][03572] Updated weights for policy 0, policy_version 60 (0.0033) [2024-12-28 00:50:29,963][01536] Fps is (10 sec: 4505.7, 60 sec: 4027.7, 300 sec: 3331.4). Total num frames: 249856. Throughput: 0: 1002.2. Samples: 61916. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:50:29,971][01536] Avg episode reward: [(0, '4.295')] [2024-12-28 00:50:34,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 262144. Throughput: 0: 972.1. Samples: 66480. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2024-12-28 00:50:34,967][01536] Avg episode reward: [(0, '4.431')] [2024-12-28 00:50:34,970][03555] Saving new best policy, reward=4.431! [2024-12-28 00:50:39,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3325.0). Total num frames: 282624. Throughput: 0: 936.0. Samples: 68336. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2024-12-28 00:50:39,968][01536] Avg episode reward: [(0, '4.568')] [2024-12-28 00:50:39,985][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth... [2024-12-28 00:50:40,125][03555] Saving new best policy, reward=4.568! [2024-12-28 00:50:40,725][03572] Updated weights for policy 0, policy_version 70 (0.0023) [2024-12-28 00:50:44,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3367.8). Total num frames: 303104. Throughput: 0: 958.2. Samples: 75154. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:50:44,965][01536] Avg episode reward: [(0, '4.532')] [2024-12-28 00:50:49,964][01536] Fps is (10 sec: 3686.1, 60 sec: 3822.9, 300 sec: 3363.0). Total num frames: 319488. Throughput: 0: 977.2. Samples: 81008. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2024-12-28 00:50:49,969][01536] Avg episode reward: [(0, '4.537')] [2024-12-28 00:50:51,361][03572] Updated weights for policy 0, policy_version 80 (0.0024) [2024-12-28 00:50:54,968][01536] Fps is (10 sec: 3684.5, 60 sec: 3754.4, 300 sec: 3399.5). Total num frames: 339968. Throughput: 0: 947.0. Samples: 83108. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:50:54,974][01536] Avg episode reward: [(0, '4.385')] [2024-12-28 00:50:59,963][01536] Fps is (10 sec: 4096.4, 60 sec: 3822.9, 300 sec: 3432.8). Total num frames: 360448. Throughput: 0: 928.2. Samples: 89214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:50:59,965][01536] Avg episode reward: [(0, '4.264')] [2024-12-28 00:51:01,125][03572] Updated weights for policy 0, policy_version 90 (0.0014) [2024-12-28 00:51:04,964][01536] Fps is (10 sec: 4097.7, 60 sec: 3891.2, 300 sec: 3463.0). Total num frames: 380928. Throughput: 0: 987.4. Samples: 96138. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:51:04,968][01536] Avg episode reward: [(0, '4.499')] [2024-12-28 00:51:09,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3454.9). Total num frames: 397312. Throughput: 0: 960.0. Samples: 98206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:09,970][01536] Avg episode reward: [(0, '4.691')] [2024-12-28 00:51:09,979][03555] Saving new best policy, reward=4.691! [2024-12-28 00:51:12,664][03572] Updated weights for policy 0, policy_version 100 (0.0019) [2024-12-28 00:51:14,963][01536] Fps is (10 sec: 3686.7, 60 sec: 3754.7, 300 sec: 3481.6). Total num frames: 417792. Throughput: 0: 923.0. Samples: 103452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:51:14,965][01536] Avg episode reward: [(0, '4.667')] [2024-12-28 00:51:19,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3538.9). Total num frames: 442368. Throughput: 0: 977.9. Samples: 110484. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:51:19,971][01536] Avg episode reward: [(0, '4.582')] [2024-12-28 00:51:21,845][03572] Updated weights for policy 0, policy_version 110 (0.0021) [2024-12-28 00:51:24,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3528.9). Total num frames: 458752. Throughput: 0: 1001.1. Samples: 113386. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:24,965][01536] Avg episode reward: [(0, '4.565')] [2024-12-28 00:51:29,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3519.5). Total num frames: 475136. Throughput: 0: 942.3. Samples: 117558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:51:29,970][01536] Avg episode reward: [(0, '4.536')] [2024-12-28 00:51:33,192][03572] Updated weights for policy 0, policy_version 120 (0.0021) [2024-12-28 00:51:34,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3569.4). Total num frames: 499712. Throughput: 0: 965.8. Samples: 124470. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:34,966][01536] Avg episode reward: [(0, '4.656')] [2024-12-28 00:51:39,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3587.5). Total num frames: 520192. Throughput: 0: 997.5. Samples: 127990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:39,972][01536] Avg episode reward: [(0, '4.652')] [2024-12-28 00:51:44,103][03572] Updated weights for policy 0, policy_version 130 (0.0027) [2024-12-28 00:51:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3549.9). Total num frames: 532480. Throughput: 0: 970.8. Samples: 132898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:51:44,970][01536] Avg episode reward: [(0, '4.729')] [2024-12-28 00:51:44,972][03555] Saving new best policy, reward=4.729! [2024-12-28 00:51:49,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3593.9). Total num frames: 557056. Throughput: 0: 951.2. Samples: 138940. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:49,966][01536] Avg episode reward: [(0, '4.587')] [2024-12-28 00:51:53,254][03572] Updated weights for policy 0, policy_version 140 (0.0023) [2024-12-28 00:51:54,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.8, 300 sec: 3609.6). Total num frames: 577536. Throughput: 0: 983.1. Samples: 142446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:51:54,970][01536] Avg episode reward: [(0, '4.298')] [2024-12-28 00:51:59,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3599.5). Total num frames: 593920. Throughput: 0: 991.5. Samples: 148070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:51:59,967][01536] Avg episode reward: [(0, '4.340')] [2024-12-28 00:52:04,963][01536] Fps is (10 sec: 3276.7, 60 sec: 3823.0, 300 sec: 3590.0). Total num frames: 610304. Throughput: 0: 945.9. Samples: 153050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:52:04,970][01536] Avg episode reward: [(0, '4.277')] [2024-12-28 00:52:05,047][03572] Updated weights for policy 0, policy_version 150 (0.0022) [2024-12-28 00:52:09,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3627.9). Total num frames: 634880. Throughput: 0: 959.7. Samples: 156574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:52:09,970][01536] Avg episode reward: [(0, '4.440')] [2024-12-28 00:52:14,422][03572] Updated weights for policy 0, policy_version 160 (0.0030) [2024-12-28 00:52:14,965][01536] Fps is (10 sec: 4504.9, 60 sec: 3959.4, 300 sec: 3640.9). Total num frames: 655360. Throughput: 0: 1020.1. Samples: 163464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:52:14,967][01536] Avg episode reward: [(0, '4.638')] [2024-12-28 00:52:19,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3631.0). Total num frames: 671744. Throughput: 0: 960.7. Samples: 167702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:52:19,966][01536] Avg episode reward: [(0, '4.527')] [2024-12-28 00:52:24,963][01536] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3643.3). Total num frames: 692224. Throughput: 0: 956.3. Samples: 171022. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:52:24,969][01536] Avg episode reward: [(0, '4.428')] [2024-12-28 00:52:25,295][03572] Updated weights for policy 0, policy_version 170 (0.0027) [2024-12-28 00:52:29,971][01536] Fps is (10 sec: 4502.2, 60 sec: 4027.2, 300 sec: 3675.8). Total num frames: 716800. Throughput: 0: 999.9. Samples: 177900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:52:29,974][01536] Avg episode reward: [(0, '4.566')] [2024-12-28 00:52:34,964][01536] Fps is (10 sec: 3686.1, 60 sec: 3822.9, 300 sec: 3645.4). Total num frames: 729088. Throughput: 0: 974.9. Samples: 182812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:52:34,967][01536] Avg episode reward: [(0, '4.603')] [2024-12-28 00:52:36,887][03572] Updated weights for policy 0, policy_version 180 (0.0024) [2024-12-28 00:52:39,963][01536] Fps is (10 sec: 3279.3, 60 sec: 3822.9, 300 sec: 3656.4). Total num frames: 749568. Throughput: 0: 947.9. Samples: 185100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 00:52:39,965][01536] Avg episode reward: [(0, '4.518')] [2024-12-28 00:52:39,973][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth... [2024-12-28 00:52:44,963][01536] Fps is (10 sec: 4505.9, 60 sec: 4027.7, 300 sec: 3686.4). Total num frames: 774144. Throughput: 0: 978.2. Samples: 192088. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-12-28 00:52:44,968][01536] Avg episode reward: [(0, '4.558')] [2024-12-28 00:52:45,542][03572] Updated weights for policy 0, policy_version 190 (0.0018) [2024-12-28 00:52:49,967][01536] Fps is (10 sec: 4094.4, 60 sec: 3891.0, 300 sec: 3676.8). Total num frames: 790528. Throughput: 0: 996.5. Samples: 197898. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:52:49,969][01536] Avg episode reward: [(0, '4.774')] [2024-12-28 00:52:49,980][03555] Saving new best policy, reward=4.774! [2024-12-28 00:52:54,964][01536] Fps is (10 sec: 3276.5, 60 sec: 3822.9, 300 sec: 3667.8). Total num frames: 806912. Throughput: 0: 963.6. Samples: 199936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:52:54,968][01536] Avg episode reward: [(0, '4.805')] [2024-12-28 00:52:54,974][03555] Saving new best policy, reward=4.805! [2024-12-28 00:52:57,515][03572] Updated weights for policy 0, policy_version 200 (0.0026) [2024-12-28 00:52:59,963][01536] Fps is (10 sec: 3687.7, 60 sec: 3891.2, 300 sec: 3677.3). Total num frames: 827392. Throughput: 0: 945.6. Samples: 206014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:52:59,965][01536] Avg episode reward: [(0, '4.633')] [2024-12-28 00:53:04,963][01536] Fps is (10 sec: 4505.9, 60 sec: 4027.7, 300 sec: 3704.2). Total num frames: 851968. Throughput: 0: 1003.6. Samples: 212864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:53:04,968][01536] Avg episode reward: [(0, '4.483')] [2024-12-28 00:53:08,083][03572] Updated weights for policy 0, policy_version 210 (0.0025) [2024-12-28 00:53:09,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3677.7). Total num frames: 864256. Throughput: 0: 975.5. Samples: 214920. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:53:09,969][01536] Avg episode reward: [(0, '4.565')] [2024-12-28 00:53:14,963][01536] Fps is (10 sec: 3276.9, 60 sec: 3823.0, 300 sec: 3686.4). Total num frames: 884736. Throughput: 0: 938.3. Samples: 220118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:53:14,969][01536] Avg episode reward: [(0, '4.586')] [2024-12-28 00:53:17,899][03572] Updated weights for policy 0, policy_version 220 (0.0015) [2024-12-28 00:53:19,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3711.5). Total num frames: 909312. Throughput: 0: 987.3. Samples: 227240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:53:19,965][01536] Avg episode reward: [(0, '4.489')] [2024-12-28 00:53:24,965][01536] Fps is (10 sec: 4095.3, 60 sec: 3891.1, 300 sec: 3702.8). Total num frames: 925696. Throughput: 0: 1004.4. Samples: 230298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:53:24,967][01536] Avg episode reward: [(0, '4.587')] [2024-12-28 00:53:29,560][03572] Updated weights for policy 0, policy_version 230 (0.0040) [2024-12-28 00:53:29,963][01536] Fps is (10 sec: 3276.7, 60 sec: 3755.1, 300 sec: 3694.4). Total num frames: 942080. Throughput: 0: 942.3. Samples: 234490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:53:29,977][01536] Avg episode reward: [(0, '4.636')] [2024-12-28 00:53:34,963][01536] Fps is (10 sec: 4096.7, 60 sec: 3959.5, 300 sec: 3717.9). Total num frames: 966656. Throughput: 0: 963.0. Samples: 241228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:53:34,974][01536] Avg episode reward: [(0, '4.560')] [2024-12-28 00:53:38,332][03572] Updated weights for policy 0, policy_version 240 (0.0025) [2024-12-28 00:53:39,965][01536] Fps is (10 sec: 4504.9, 60 sec: 3959.4, 300 sec: 3725.0). Total num frames: 987136. Throughput: 0: 997.0. Samples: 244800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:53:39,974][01536] Avg episode reward: [(0, '4.500')] [2024-12-28 00:53:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3701.6). Total num frames: 999424. Throughput: 0: 970.1. Samples: 249670. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:53:44,970][01536] Avg episode reward: [(0, '4.614')] [2024-12-28 00:53:49,847][03572] Updated weights for policy 0, policy_version 250 (0.0031) [2024-12-28 00:53:49,963][01536] Fps is (10 sec: 3687.0, 60 sec: 3891.5, 300 sec: 3723.6). Total num frames: 1024000. Throughput: 0: 949.9. Samples: 255610. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2024-12-28 00:53:49,970][01536] Avg episode reward: [(0, '4.584')] [2024-12-28 00:53:54,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3730.3). Total num frames: 1044480. Throughput: 0: 981.8. Samples: 259102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:53:54,966][01536] Avg episode reward: [(0, '4.515')] [2024-12-28 00:53:59,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3722.3). Total num frames: 1060864. Throughput: 0: 995.7. Samples: 264924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:53:59,966][01536] Avg episode reward: [(0, '4.751')] [2024-12-28 00:54:00,661][03572] Updated weights for policy 0, policy_version 260 (0.0025) [2024-12-28 00:54:04,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3714.6). Total num frames: 1077248. Throughput: 0: 944.0. Samples: 269722. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:54:04,968][01536] Avg episode reward: [(0, '4.652')] [2024-12-28 00:54:09,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3735.0). Total num frames: 1101824. Throughput: 0: 952.9. Samples: 273176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:54:09,969][01536] Avg episode reward: [(0, '4.477')] [2024-12-28 00:54:10,276][03572] Updated weights for policy 0, policy_version 270 (0.0027) [2024-12-28 00:54:14,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3804.4). Total num frames: 1122304. Throughput: 0: 1016.4. Samples: 280228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:14,969][01536] Avg episode reward: [(0, '4.678')] [2024-12-28 00:54:19,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 1134592. Throughput: 0: 960.6. Samples: 284456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:54:19,969][01536] Avg episode reward: [(0, '4.798')] [2024-12-28 00:54:21,746][03572] Updated weights for policy 0, policy_version 280 (0.0025) [2024-12-28 00:54:24,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3901.6). Total num frames: 1159168. Throughput: 0: 952.9. Samples: 287678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:24,968][01536] Avg episode reward: [(0, '4.718')] [2024-12-28 00:54:29,965][01536] Fps is (10 sec: 4914.3, 60 sec: 4027.6, 300 sec: 3901.6). Total num frames: 1183744. Throughput: 0: 998.4. Samples: 294602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:29,971][01536] Avg episode reward: [(0, '4.673')] [2024-12-28 00:54:30,978][03572] Updated weights for policy 0, policy_version 290 (0.0018) [2024-12-28 00:54:34,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1196032. Throughput: 0: 978.7. Samples: 299652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:34,973][01536] Avg episode reward: [(0, '4.698')] [2024-12-28 00:54:39,963][01536] Fps is (10 sec: 3277.3, 60 sec: 3823.0, 300 sec: 3887.7). Total num frames: 1216512. Throughput: 0: 953.6. Samples: 302014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:39,965][01536] Avg episode reward: [(0, '4.641')] [2024-12-28 00:54:39,978][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000297_1216512.pth... [2024-12-28 00:54:40,105][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth [2024-12-28 00:54:41,995][03572] Updated weights for policy 0, policy_version 300 (0.0020) [2024-12-28 00:54:44,966][01536] Fps is (10 sec: 4504.4, 60 sec: 4027.5, 300 sec: 3901.6). Total num frames: 1241088. Throughput: 0: 981.4. Samples: 309090. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:54:44,968][01536] Avg episode reward: [(0, '4.829')] [2024-12-28 00:54:44,973][03555] Saving new best policy, reward=4.829! [2024-12-28 00:54:49,965][01536] Fps is (10 sec: 4095.4, 60 sec: 3891.1, 300 sec: 3873.8). Total num frames: 1257472. Throughput: 0: 1006.3. Samples: 315008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:54:49,967][01536] Avg episode reward: [(0, '5.118')] [2024-12-28 00:54:49,977][03555] Saving new best policy, reward=5.118! [2024-12-28 00:54:53,461][03572] Updated weights for policy 0, policy_version 310 (0.0019) [2024-12-28 00:54:54,963][01536] Fps is (10 sec: 3277.7, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 1273856. Throughput: 0: 974.9. Samples: 317046. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:54:54,965][01536] Avg episode reward: [(0, '5.038')] [2024-12-28 00:54:59,963][01536] Fps is (10 sec: 4096.7, 60 sec: 3959.5, 300 sec: 3901.6). Total num frames: 1298432. Throughput: 0: 955.3. Samples: 323218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:54:59,966][01536] Avg episode reward: [(0, '4.927')] [2024-12-28 00:55:02,278][03572] Updated weights for policy 0, policy_version 320 (0.0014) [2024-12-28 00:55:04,963][01536] Fps is (10 sec: 4505.5, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 1318912. Throughput: 0: 1017.8. Samples: 330256. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:55:04,968][01536] Avg episode reward: [(0, '4.614')] [2024-12-28 00:55:09,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 1335296. Throughput: 0: 994.0. Samples: 332406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:55:09,965][01536] Avg episode reward: [(0, '4.769')] [2024-12-28 00:55:13,634][03572] Updated weights for policy 0, policy_version 330 (0.0015) [2024-12-28 00:55:14,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 1355776. Throughput: 0: 960.2. Samples: 337808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:55:14,965][01536] Avg episode reward: [(0, '5.020')] [2024-12-28 00:55:19,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3901.6). Total num frames: 1380352. Throughput: 0: 1005.6. Samples: 344904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:55:19,970][01536] Avg episode reward: [(0, '5.066')] [2024-12-28 00:55:23,059][03572] Updated weights for policy 0, policy_version 340 (0.0026) [2024-12-28 00:55:24,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 1396736. Throughput: 0: 1021.7. Samples: 347992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:55:24,967][01536] Avg episode reward: [(0, '5.124')] [2024-12-28 00:55:24,969][03555] Saving new best policy, reward=5.124! [2024-12-28 00:55:29,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3901.6). Total num frames: 1413120. Throughput: 0: 957.2. Samples: 352162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:55:29,966][01536] Avg episode reward: [(0, '5.076')] [2024-12-28 00:55:33,734][03572] Updated weights for policy 0, policy_version 350 (0.0031) [2024-12-28 00:55:34,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 1437696. Throughput: 0: 984.8. Samples: 359324. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:55:34,965][01536] Avg episode reward: [(0, '5.030')] [2024-12-28 00:55:39,965][01536] Fps is (10 sec: 4504.6, 60 sec: 4027.6, 300 sec: 3915.5). Total num frames: 1458176. Throughput: 0: 1019.4. Samples: 362922. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:55:39,971][01536] Avg episode reward: [(0, '5.211')] [2024-12-28 00:55:39,980][03555] Saving new best policy, reward=5.211! [2024-12-28 00:55:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3901.6). Total num frames: 1470464. Throughput: 0: 986.5. Samples: 367610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:55:44,966][01536] Avg episode reward: [(0, '5.221')] [2024-12-28 00:55:44,972][03555] Saving new best policy, reward=5.221! [2024-12-28 00:55:45,286][03572] Updated weights for policy 0, policy_version 360 (0.0021) [2024-12-28 00:55:49,963][01536] Fps is (10 sec: 3687.2, 60 sec: 3959.6, 300 sec: 3915.6). Total num frames: 1495040. Throughput: 0: 967.6. Samples: 373796. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:55:49,969][01536] Avg episode reward: [(0, '5.019')] [2024-12-28 00:55:53,851][03572] Updated weights for policy 0, policy_version 370 (0.0017) [2024-12-28 00:55:54,965][01536] Fps is (10 sec: 4914.3, 60 sec: 4095.9, 300 sec: 3929.4). Total num frames: 1519616. Throughput: 0: 999.5. Samples: 377386. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:55:54,973][01536] Avg episode reward: [(0, '4.863')] [2024-12-28 00:55:59,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 1531904. Throughput: 0: 1003.5. Samples: 382964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:55:59,968][01536] Avg episode reward: [(0, '4.998')] [2024-12-28 00:56:04,963][01536] Fps is (10 sec: 3277.4, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 1552384. Throughput: 0: 962.8. Samples: 388230. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:56:04,969][01536] Avg episode reward: [(0, '5.375')] [2024-12-28 00:56:04,974][03555] Saving new best policy, reward=5.375! [2024-12-28 00:56:05,270][03572] Updated weights for policy 0, policy_version 380 (0.0053) [2024-12-28 00:56:09,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1576960. Throughput: 0: 971.8. Samples: 391724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:56:09,970][01536] Avg episode reward: [(0, '5.554')] [2024-12-28 00:56:09,981][03555] Saving new best policy, reward=5.554! [2024-12-28 00:56:14,964][01536] Fps is (10 sec: 4095.7, 60 sec: 3959.4, 300 sec: 3901.6). Total num frames: 1593344. Throughput: 0: 1025.9. Samples: 398330. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:56:14,969][01536] Avg episode reward: [(0, '5.383')] [2024-12-28 00:56:15,559][03572] Updated weights for policy 0, policy_version 390 (0.0025) [2024-12-28 00:56:19,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 1609728. Throughput: 0: 962.9. Samples: 402654. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:56:19,965][01536] Avg episode reward: [(0, '5.340')] [2024-12-28 00:56:24,963][01536] Fps is (10 sec: 4096.3, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 1634304. Throughput: 0: 962.2. Samples: 406220. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:56:24,965][01536] Avg episode reward: [(0, '5.679')] [2024-12-28 00:56:24,971][03555] Saving new best policy, reward=5.679! [2024-12-28 00:56:25,529][03572] Updated weights for policy 0, policy_version 400 (0.0018) [2024-12-28 00:56:29,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 1654784. Throughput: 0: 1011.8. Samples: 413140. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2024-12-28 00:56:29,969][01536] Avg episode reward: [(0, '6.286')] [2024-12-28 00:56:29,985][03555] Saving new best policy, reward=6.286! [2024-12-28 00:56:34,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 1667072. Throughput: 0: 976.8. Samples: 417752. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:56:34,969][01536] Avg episode reward: [(0, '5.960')] [2024-12-28 00:56:37,174][03572] Updated weights for policy 0, policy_version 410 (0.0032) [2024-12-28 00:56:39,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.4, 300 sec: 3929.4). Total num frames: 1691648. Throughput: 0: 957.7. Samples: 420480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:56:39,969][01536] Avg episode reward: [(0, '6.220')] [2024-12-28 00:56:39,978][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000413_1691648.pth... [2024-12-28 00:56:40,128][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000183_749568.pth [2024-12-28 00:56:44,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3929.4). Total num frames: 1716224. Throughput: 0: 992.7. Samples: 427636. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:56:44,971][01536] Avg episode reward: [(0, '6.545')] [2024-12-28 00:56:44,973][03555] Saving new best policy, reward=6.545! [2024-12-28 00:56:45,740][03572] Updated weights for policy 0, policy_version 420 (0.0018) [2024-12-28 00:56:49,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 1732608. Throughput: 0: 1000.3. Samples: 433242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:56:49,966][01536] Avg episode reward: [(0, '6.595')] [2024-12-28 00:56:49,994][03555] Saving new best policy, reward=6.595! [2024-12-28 00:56:54,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3915.5). Total num frames: 1748992. Throughput: 0: 968.6. Samples: 435310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:56:54,968][01536] Avg episode reward: [(0, '6.512')] [2024-12-28 00:56:57,087][03572] Updated weights for policy 0, policy_version 430 (0.0040) [2024-12-28 00:56:59,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1773568. Throughput: 0: 968.6. Samples: 441918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:56:59,965][01536] Avg episode reward: [(0, '6.457')] [2024-12-28 00:57:04,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1794048. Throughput: 0: 1019.1. Samples: 448512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:57:04,971][01536] Avg episode reward: [(0, '6.741')] [2024-12-28 00:57:04,978][03555] Saving new best policy, reward=6.741! [2024-12-28 00:57:07,739][03572] Updated weights for policy 0, policy_version 440 (0.0015) [2024-12-28 00:57:09,963][01536] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 1806336. Throughput: 0: 985.1. Samples: 450552. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 00:57:09,966][01536] Avg episode reward: [(0, '6.583')] [2024-12-28 00:57:14,963][01536] Fps is (10 sec: 3686.3, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 1830912. Throughput: 0: 959.7. Samples: 456326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:57:14,968][01536] Avg episode reward: [(0, '6.552')] [2024-12-28 00:57:17,307][03572] Updated weights for policy 0, policy_version 450 (0.0028) [2024-12-28 00:57:19,963][01536] Fps is (10 sec: 4915.3, 60 sec: 4096.0, 300 sec: 3943.3). Total num frames: 1855488. Throughput: 0: 1016.5. Samples: 463494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:57:19,966][01536] Avg episode reward: [(0, '6.430')] [2024-12-28 00:57:24,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3901.7). Total num frames: 1867776. Throughput: 0: 1012.8. Samples: 466058. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 00:57:24,968][01536] Avg episode reward: [(0, '6.739')] [2024-12-28 00:57:29,017][03572] Updated weights for policy 0, policy_version 460 (0.0024) [2024-12-28 00:57:29,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 1888256. Throughput: 0: 956.7. Samples: 470686. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:57:29,968][01536] Avg episode reward: [(0, '6.727')] [2024-12-28 00:57:34,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3943.3). Total num frames: 1912832. Throughput: 0: 986.9. Samples: 477654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:57:34,971][01536] Avg episode reward: [(0, '6.342')] [2024-12-28 00:57:38,097][03572] Updated weights for policy 0, policy_version 470 (0.0035) [2024-12-28 00:57:39,965][01536] Fps is (10 sec: 4095.3, 60 sec: 3959.3, 300 sec: 3915.5). Total num frames: 1929216. Throughput: 0: 1016.7. Samples: 481062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:57:39,970][01536] Avg episode reward: [(0, '5.901')] [2024-12-28 00:57:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 1945600. Throughput: 0: 964.5. Samples: 485322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:57:44,967][01536] Avg episode reward: [(0, '5.430')] [2024-12-28 00:57:48,949][03572] Updated weights for policy 0, policy_version 480 (0.0030) [2024-12-28 00:57:49,963][01536] Fps is (10 sec: 4096.7, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1970176. Throughput: 0: 968.3. Samples: 492084. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 00:57:49,967][01536] Avg episode reward: [(0, '5.878')] [2024-12-28 00:57:54,966][01536] Fps is (10 sec: 4504.4, 60 sec: 4027.5, 300 sec: 3943.2). Total num frames: 1990656. Throughput: 0: 1002.6. Samples: 495672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:57:54,968][01536] Avg episode reward: [(0, '6.057')] [2024-12-28 00:57:59,965][01536] Fps is (10 sec: 3276.2, 60 sec: 3822.8, 300 sec: 3901.6). Total num frames: 2002944. Throughput: 0: 984.6. Samples: 500636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 00:57:59,967][01536] Avg episode reward: [(0, '5.872')] [2024-12-28 00:58:00,445][03572] Updated weights for policy 0, policy_version 490 (0.0025) [2024-12-28 00:58:04,963][01536] Fps is (10 sec: 3277.7, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 2023424. Throughput: 0: 951.6. Samples: 506314. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2024-12-28 00:58:04,965][01536] Avg episode reward: [(0, '6.006')] [2024-12-28 00:58:09,431][03572] Updated weights for policy 0, policy_version 500 (0.0019) [2024-12-28 00:58:09,963][01536] Fps is (10 sec: 4506.4, 60 sec: 4027.8, 300 sec: 3943.3). Total num frames: 2048000. Throughput: 0: 972.8. Samples: 509832. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 00:58:09,965][01536] Avg episode reward: [(0, '6.389')] [2024-12-28 00:58:14,964][01536] Fps is (10 sec: 4095.7, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 2064384. Throughput: 0: 1009.3. Samples: 516104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:14,967][01536] Avg episode reward: [(0, '6.677')] [2024-12-28 00:58:19,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 2084864. Throughput: 0: 961.9. Samples: 520940. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:19,969][01536] Avg episode reward: [(0, '6.662')] [2024-12-28 00:58:20,745][03572] Updated weights for policy 0, policy_version 510 (0.0021) [2024-12-28 00:58:24,963][01536] Fps is (10 sec: 4506.0, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 2109440. Throughput: 0: 966.0. Samples: 524530. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:24,966][01536] Avg episode reward: [(0, '6.862')] [2024-12-28 00:58:24,971][03555] Saving new best policy, reward=6.862! [2024-12-28 00:58:29,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 2125824. Throughput: 0: 1025.2. Samples: 531454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:58:29,970][01536] Avg episode reward: [(0, '6.668')] [2024-12-28 00:58:30,457][03572] Updated weights for policy 0, policy_version 520 (0.0015) [2024-12-28 00:58:34,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 2142208. Throughput: 0: 968.4. Samples: 535664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:34,967][01536] Avg episode reward: [(0, '6.789')] [2024-12-28 00:58:39,965][01536] Fps is (10 sec: 4095.3, 60 sec: 3959.5, 300 sec: 3957.1). Total num frames: 2166784. Throughput: 0: 957.8. Samples: 538774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:58:39,971][01536] Avg episode reward: [(0, '6.370')] [2024-12-28 00:58:39,982][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000529_2166784.pth... [2024-12-28 00:58:40,119][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000297_1216512.pth [2024-12-28 00:58:40,902][03572] Updated weights for policy 0, policy_version 530 (0.0027) [2024-12-28 00:58:44,964][01536] Fps is (10 sec: 4505.3, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 2187264. Throughput: 0: 1004.6. Samples: 545844. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:58:44,972][01536] Avg episode reward: [(0, '6.577')] [2024-12-28 00:58:49,963][01536] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2203648. Throughput: 0: 995.2. Samples: 551098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:49,968][01536] Avg episode reward: [(0, '6.546')] [2024-12-28 00:58:52,213][03572] Updated weights for policy 0, policy_version 540 (0.0013) [2024-12-28 00:58:54,963][01536] Fps is (10 sec: 3686.7, 60 sec: 3891.4, 300 sec: 3943.3). Total num frames: 2224128. Throughput: 0: 967.6. Samples: 553372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:54,968][01536] Avg episode reward: [(0, '6.779')] [2024-12-28 00:58:59,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 3957.2). Total num frames: 2244608. Throughput: 0: 987.6. Samples: 560544. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:58:59,965][01536] Avg episode reward: [(0, '6.789')] [2024-12-28 00:59:00,966][03572] Updated weights for policy 0, policy_version 550 (0.0022) [2024-12-28 00:59:04,965][01536] Fps is (10 sec: 4095.0, 60 sec: 4027.6, 300 sec: 3943.2). Total num frames: 2265088. Throughput: 0: 1013.3. Samples: 566540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:59:04,968][01536] Avg episode reward: [(0, '6.961')] [2024-12-28 00:59:04,970][03555] Saving new best policy, reward=6.961! [2024-12-28 00:59:09,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2281472. Throughput: 0: 979.4. Samples: 568602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:59:09,965][01536] Avg episode reward: [(0, '7.006')] [2024-12-28 00:59:09,979][03555] Saving new best policy, reward=7.006! [2024-12-28 00:59:12,457][03572] Updated weights for policy 0, policy_version 560 (0.0017) [2024-12-28 00:59:14,963][01536] Fps is (10 sec: 3687.3, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2301952. Throughput: 0: 964.2. Samples: 574842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 00:59:14,971][01536] Avg episode reward: [(0, '7.668')] [2024-12-28 00:59:15,009][03555] Saving new best policy, reward=7.668! [2024-12-28 00:59:19,963][01536] Fps is (10 sec: 4505.5, 60 sec: 4027.7, 300 sec: 3957.1). Total num frames: 2326528. Throughput: 0: 1029.6. Samples: 581994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:59:19,967][01536] Avg episode reward: [(0, '7.955')] [2024-12-28 00:59:19,977][03555] Saving new best policy, reward=7.955! [2024-12-28 00:59:22,293][03572] Updated weights for policy 0, policy_version 570 (0.0016) [2024-12-28 00:59:24,969][01536] Fps is (10 sec: 4093.7, 60 sec: 3890.8, 300 sec: 3929.3). Total num frames: 2342912. Throughput: 0: 1007.5. Samples: 584114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 00:59:24,971][01536] Avg episode reward: [(0, '8.082')] [2024-12-28 00:59:24,973][03555] Saving new best policy, reward=8.082! [2024-12-28 00:59:29,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2363392. Throughput: 0: 965.9. Samples: 589308. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:59:29,970][01536] Avg episode reward: [(0, '8.144')] [2024-12-28 00:59:29,979][03555] Saving new best policy, reward=8.144! [2024-12-28 00:59:32,453][03572] Updated weights for policy 0, policy_version 580 (0.0015) [2024-12-28 00:59:34,963][01536] Fps is (10 sec: 4098.3, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 2383872. Throughput: 0: 1004.9. Samples: 596320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:59:34,965][01536] Avg episode reward: [(0, '9.861')] [2024-12-28 00:59:35,068][03555] Saving new best policy, reward=9.861! [2024-12-28 00:59:39,965][01536] Fps is (10 sec: 3685.8, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2400256. Throughput: 0: 1021.4. Samples: 599338. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 00:59:39,967][01536] Avg episode reward: [(0, '9.940')] [2024-12-28 00:59:39,982][03555] Saving new best policy, reward=9.940! [2024-12-28 00:59:44,080][03572] Updated weights for policy 0, policy_version 590 (0.0021) [2024-12-28 00:59:44,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2420736. Throughput: 0: 957.2. Samples: 603616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:59:44,965][01536] Avg episode reward: [(0, '9.563')] [2024-12-28 00:59:49,963][01536] Fps is (10 sec: 4096.7, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2441216. Throughput: 0: 982.1. Samples: 610734. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:59:49,970][01536] Avg episode reward: [(0, '10.290')] [2024-12-28 00:59:50,007][03555] Saving new best policy, reward=10.290! [2024-12-28 00:59:52,564][03572] Updated weights for policy 0, policy_version 600 (0.0020) [2024-12-28 00:59:54,971][01536] Fps is (10 sec: 4092.8, 60 sec: 3959.0, 300 sec: 3943.2). Total num frames: 2461696. Throughput: 0: 1014.4. Samples: 614260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 00:59:54,983][01536] Avg episode reward: [(0, '9.966')] [2024-12-28 00:59:59,964][01536] Fps is (10 sec: 3686.1, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2478080. Throughput: 0: 982.7. Samples: 619066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 00:59:59,971][01536] Avg episode reward: [(0, '10.722')] [2024-12-28 00:59:59,981][03555] Saving new best policy, reward=10.722! [2024-12-28 01:00:04,099][03572] Updated weights for policy 0, policy_version 610 (0.0032) [2024-12-28 01:00:04,963][01536] Fps is (10 sec: 4099.2, 60 sec: 3959.6, 300 sec: 3957.2). Total num frames: 2502656. Throughput: 0: 959.3. Samples: 625162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:00:04,967][01536] Avg episode reward: [(0, '12.032')] [2024-12-28 01:00:04,969][03555] Saving new best policy, reward=12.032! [2024-12-28 01:00:09,963][01536] Fps is (10 sec: 4505.8, 60 sec: 4027.7, 300 sec: 3957.1). Total num frames: 2523136. Throughput: 0: 990.2. Samples: 628668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:00:09,969][01536] Avg episode reward: [(0, '12.072')] [2024-12-28 01:00:09,976][03555] Saving new best policy, reward=12.072! [2024-12-28 01:00:14,447][03572] Updated weights for policy 0, policy_version 620 (0.0041) [2024-12-28 01:00:14,966][01536] Fps is (10 sec: 3685.4, 60 sec: 3959.3, 300 sec: 3929.3). Total num frames: 2539520. Throughput: 0: 1001.5. Samples: 634378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:00:14,970][01536] Avg episode reward: [(0, '12.468')] [2024-12-28 01:00:14,984][03555] Saving new best policy, reward=12.468! [2024-12-28 01:00:19,963][01536] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2560000. Throughput: 0: 962.9. Samples: 639650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:00:19,965][01536] Avg episode reward: [(0, '13.224')] [2024-12-28 01:00:19,973][03555] Saving new best policy, reward=13.224! [2024-12-28 01:00:24,261][03572] Updated weights for policy 0, policy_version 630 (0.0029) [2024-12-28 01:00:24,963][01536] Fps is (10 sec: 4097.1, 60 sec: 3959.8, 300 sec: 3957.2). Total num frames: 2580480. Throughput: 0: 973.9. Samples: 643162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:00:24,965][01536] Avg episode reward: [(0, '12.588')] [2024-12-28 01:00:29,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2600960. Throughput: 0: 1029.1. Samples: 649924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:00:29,966][01536] Avg episode reward: [(0, '12.121')] [2024-12-28 01:00:34,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2617344. Throughput: 0: 966.2. Samples: 654212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:00:34,971][01536] Avg episode reward: [(0, '11.842')] [2024-12-28 01:00:35,573][03572] Updated weights for policy 0, policy_version 640 (0.0029) [2024-12-28 01:00:39,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 3971.0). Total num frames: 2641920. Throughput: 0: 965.5. Samples: 657700. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:00:39,965][01536] Avg episode reward: [(0, '11.370')] [2024-12-28 01:00:39,973][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000645_2641920.pth... [2024-12-28 01:00:40,096][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000413_1691648.pth [2024-12-28 01:00:44,100][03572] Updated weights for policy 0, policy_version 650 (0.0025) [2024-12-28 01:00:44,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 2662400. Throughput: 0: 1018.6. Samples: 664900. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:00:44,965][01536] Avg episode reward: [(0, '11.791')] [2024-12-28 01:00:49,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 2678784. Throughput: 0: 990.9. Samples: 669754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:00:49,966][01536] Avg episode reward: [(0, '11.671')] [2024-12-28 01:00:54,963][01536] Fps is (10 sec: 3686.3, 60 sec: 3960.0, 300 sec: 3957.2). Total num frames: 2699264. Throughput: 0: 969.9. Samples: 672312. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:00:54,966][01536] Avg episode reward: [(0, '12.078')] [2024-12-28 01:00:55,439][03572] Updated weights for policy 0, policy_version 660 (0.0027) [2024-12-28 01:00:59,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.1, 300 sec: 3971.0). Total num frames: 2723840. Throughput: 0: 1005.2. Samples: 679608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:00:59,967][01536] Avg episode reward: [(0, '12.629')] [2024-12-28 01:01:04,963][01536] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2740224. Throughput: 0: 1015.5. Samples: 685346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:01:04,967][01536] Avg episode reward: [(0, '13.163')] [2024-12-28 01:01:05,873][03572] Updated weights for policy 0, policy_version 670 (0.0018) [2024-12-28 01:01:09,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2756608. Throughput: 0: 985.4. Samples: 687506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:01:09,968][01536] Avg episode reward: [(0, '13.396')] [2024-12-28 01:01:09,978][03555] Saving new best policy, reward=13.396! [2024-12-28 01:01:14,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 3971.0). Total num frames: 2781184. Throughput: 0: 982.2. Samples: 694122. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:01:14,969][01536] Avg episode reward: [(0, '15.376')] [2024-12-28 01:01:14,972][03555] Saving new best policy, reward=15.376! [2024-12-28 01:01:15,516][03572] Updated weights for policy 0, policy_version 680 (0.0023) [2024-12-28 01:01:19,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 2801664. Throughput: 0: 1038.0. Samples: 700922. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:01:19,970][01536] Avg episode reward: [(0, '15.010')] [2024-12-28 01:01:24,965][01536] Fps is (10 sec: 3685.7, 60 sec: 3959.3, 300 sec: 3943.2). Total num frames: 2818048. Throughput: 0: 1007.2. Samples: 703026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:01:24,969][01536] Avg episode reward: [(0, '15.137')] [2024-12-28 01:01:26,635][03572] Updated weights for policy 0, policy_version 690 (0.0021) [2024-12-28 01:01:29,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 2838528. Throughput: 0: 974.7. Samples: 708762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:01:29,965][01536] Avg episode reward: [(0, '15.231')] [2024-12-28 01:01:34,963][01536] Fps is (10 sec: 4506.5, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 2863104. Throughput: 0: 1023.1. Samples: 715792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:01:34,965][01536] Avg episode reward: [(0, '14.816')] [2024-12-28 01:01:35,459][03572] Updated weights for policy 0, policy_version 700 (0.0024) [2024-12-28 01:01:39,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2879488. Throughput: 0: 1025.8. Samples: 718474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:01:39,965][01536] Avg episode reward: [(0, '15.190')] [2024-12-28 01:01:44,963][01536] Fps is (10 sec: 3686.3, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2899968. Throughput: 0: 970.0. Samples: 723260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:01:44,969][01536] Avg episode reward: [(0, '15.794')] [2024-12-28 01:01:44,973][03555] Saving new best policy, reward=15.794! [2024-12-28 01:01:46,734][03572] Updated weights for policy 0, policy_version 710 (0.0036) [2024-12-28 01:01:49,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2920448. Throughput: 0: 999.6. Samples: 730326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:01:49,972][01536] Avg episode reward: [(0, '16.322')] [2024-12-28 01:01:49,984][03555] Saving new best policy, reward=16.322! [2024-12-28 01:01:54,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3957.1). Total num frames: 2940928. Throughput: 0: 1027.5. Samples: 733744. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:01:54,969][01536] Avg episode reward: [(0, '15.441')] [2024-12-28 01:01:57,983][03572] Updated weights for policy 0, policy_version 720 (0.0032) [2024-12-28 01:01:59,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 2953216. Throughput: 0: 973.3. Samples: 737922. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:01:59,966][01536] Avg episode reward: [(0, '15.676')] [2024-12-28 01:02:04,964][01536] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3971.0). Total num frames: 2977792. Throughput: 0: 963.4. Samples: 744276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:02:04,967][01536] Avg episode reward: [(0, '16.338')] [2024-12-28 01:02:04,968][03555] Saving new best policy, reward=16.338! [2024-12-28 01:02:07,405][03572] Updated weights for policy 0, policy_version 730 (0.0023) [2024-12-28 01:02:09,967][01536] Fps is (10 sec: 4503.9, 60 sec: 4027.5, 300 sec: 3957.1). Total num frames: 2998272. Throughput: 0: 993.3. Samples: 747726. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:02:09,969][01536] Avg episode reward: [(0, '15.965')] [2024-12-28 01:02:14,963][01536] Fps is (10 sec: 3686.6, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 3014656. Throughput: 0: 980.2. Samples: 752872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:02:14,968][01536] Avg episode reward: [(0, '17.279')] [2024-12-28 01:02:14,974][03555] Saving new best policy, reward=17.279! [2024-12-28 01:02:19,066][03572] Updated weights for policy 0, policy_version 740 (0.0027) [2024-12-28 01:02:19,963][01536] Fps is (10 sec: 3687.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3035136. Throughput: 0: 943.6. Samples: 758254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 01:02:19,966][01536] Avg episode reward: [(0, '18.833')] [2024-12-28 01:02:19,978][03555] Saving new best policy, reward=18.833! [2024-12-28 01:02:24,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3957.2). Total num frames: 3055616. Throughput: 0: 958.5. Samples: 761606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:02:24,968][01536] Avg episode reward: [(0, '19.851')] [2024-12-28 01:02:24,970][03555] Saving new best policy, reward=19.851! [2024-12-28 01:02:29,063][03572] Updated weights for policy 0, policy_version 750 (0.0025) [2024-12-28 01:02:29,963][01536] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 3072000. Throughput: 0: 987.8. Samples: 767712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:02:29,966][01536] Avg episode reward: [(0, '19.718')] [2024-12-28 01:02:34,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3929.4). Total num frames: 3088384. Throughput: 0: 928.2. Samples: 772094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 01:02:34,967][01536] Avg episode reward: [(0, '19.802')] [2024-12-28 01:02:39,715][03572] Updated weights for policy 0, policy_version 760 (0.0019) [2024-12-28 01:02:39,964][01536] Fps is (10 sec: 4095.7, 60 sec: 3891.1, 300 sec: 3957.1). Total num frames: 3112960. Throughput: 0: 931.8. Samples: 775674. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:02:39,967][01536] Avg episode reward: [(0, '19.413')] [2024-12-28 01:02:39,980][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000760_3112960.pth... [2024-12-28 01:02:40,104][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000529_2166784.pth [2024-12-28 01:02:44,963][01536] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3133440. Throughput: 0: 997.2. Samples: 782796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:02:44,965][01536] Avg episode reward: [(0, '18.069')] [2024-12-28 01:02:49,963][01536] Fps is (10 sec: 3277.1, 60 sec: 3754.7, 300 sec: 3915.5). Total num frames: 3145728. Throughput: 0: 956.1. Samples: 787300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:02:49,971][01536] Avg episode reward: [(0, '17.441')] [2024-12-28 01:02:51,103][03572] Updated weights for policy 0, policy_version 770 (0.0019) [2024-12-28 01:02:54,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3957.2). Total num frames: 3170304. Throughput: 0: 941.2. Samples: 790078. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 01:02:54,969][01536] Avg episode reward: [(0, '17.108')] [2024-12-28 01:02:59,825][03572] Updated weights for policy 0, policy_version 780 (0.0014) [2024-12-28 01:02:59,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 3194880. Throughput: 0: 986.8. Samples: 797280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:02:59,965][01536] Avg episode reward: [(0, '15.594')] [2024-12-28 01:03:04,966][01536] Fps is (10 sec: 3685.4, 60 sec: 3822.8, 300 sec: 3929.3). Total num frames: 3207168. Throughput: 0: 987.1. Samples: 802674. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:03:04,969][01536] Avg episode reward: [(0, '16.468')] [2024-12-28 01:03:09,967][01536] Fps is (10 sec: 3275.4, 60 sec: 3822.9, 300 sec: 3943.2). Total num frames: 3227648. Throughput: 0: 960.7. Samples: 804844. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:03:09,974][01536] Avg episode reward: [(0, '16.685')] [2024-12-28 01:03:11,405][03572] Updated weights for policy 0, policy_version 790 (0.0017) [2024-12-28 01:03:14,963][01536] Fps is (10 sec: 4506.8, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3252224. Throughput: 0: 977.0. Samples: 811678. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:03:14,969][01536] Avg episode reward: [(0, '16.975')] [2024-12-28 01:03:19,963][01536] Fps is (10 sec: 4507.6, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3272704. Throughput: 0: 1028.1. Samples: 818360. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 01:03:19,967][01536] Avg episode reward: [(0, '18.042')] [2024-12-28 01:03:21,039][03572] Updated weights for policy 0, policy_version 800 (0.0024) [2024-12-28 01:03:24,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 3284992. Throughput: 0: 994.2. Samples: 820414. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 01:03:24,965][01536] Avg episode reward: [(0, '18.097')] [2024-12-28 01:03:29,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3309568. Throughput: 0: 965.2. Samples: 826228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:03:29,970][01536] Avg episode reward: [(0, '17.698')] [2024-12-28 01:03:31,154][03572] Updated weights for policy 0, policy_version 810 (0.0026) [2024-12-28 01:03:34,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 3334144. Throughput: 0: 1021.4. Samples: 833264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:03:34,965][01536] Avg episode reward: [(0, '17.061')] [2024-12-28 01:03:39,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 3929.4). Total num frames: 3346432. Throughput: 0: 1017.5. Samples: 835866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:03:39,967][01536] Avg episode reward: [(0, '17.024')] [2024-12-28 01:03:42,591][03572] Updated weights for policy 0, policy_version 820 (0.0032) [2024-12-28 01:03:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3366912. Throughput: 0: 966.5. Samples: 840772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:03:44,967][01536] Avg episode reward: [(0, '17.752')] [2024-12-28 01:03:49,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 3391488. Throughput: 0: 1007.2. Samples: 847996. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2024-12-28 01:03:49,969][01536] Avg episode reward: [(0, '17.954')] [2024-12-28 01:03:51,178][03572] Updated weights for policy 0, policy_version 830 (0.0026) [2024-12-28 01:03:54,963][01536] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3407872. Throughput: 0: 1036.9. Samples: 851502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:03:54,966][01536] Avg episode reward: [(0, '17.200')] [2024-12-28 01:03:59,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 3424256. Throughput: 0: 981.2. Samples: 855832. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:03:59,965][01536] Avg episode reward: [(0, '16.630')] [2024-12-28 01:04:02,598][03572] Updated weights for policy 0, policy_version 840 (0.0021) [2024-12-28 01:04:04,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4027.9, 300 sec: 3957.2). Total num frames: 3448832. Throughput: 0: 980.9. Samples: 862502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:04:04,965][01536] Avg episode reward: [(0, '16.438')] [2024-12-28 01:04:09,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4096.3, 300 sec: 3971.0). Total num frames: 3473408. Throughput: 0: 1014.6. Samples: 866070. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2024-12-28 01:04:09,973][01536] Avg episode reward: [(0, '16.145')] [2024-12-28 01:04:12,560][03572] Updated weights for policy 0, policy_version 850 (0.0016) [2024-12-28 01:04:14,965][01536] Fps is (10 sec: 3685.8, 60 sec: 3891.1, 300 sec: 3929.4). Total num frames: 3485696. Throughput: 0: 999.9. Samples: 871226. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-12-28 01:04:14,967][01536] Avg episode reward: [(0, '16.883')] [2024-12-28 01:04:19,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3510272. Throughput: 0: 975.8. Samples: 877174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:04:19,970][01536] Avg episode reward: [(0, '18.824')] [2024-12-28 01:04:22,310][03572] Updated weights for policy 0, policy_version 860 (0.0031) [2024-12-28 01:04:24,963][01536] Fps is (10 sec: 4916.1, 60 sec: 4164.3, 300 sec: 3971.0). Total num frames: 3534848. Throughput: 0: 998.9. Samples: 880816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:04:24,965][01536] Avg episode reward: [(0, '19.270')] [2024-12-28 01:04:29,964][01536] Fps is (10 sec: 4095.5, 60 sec: 4027.7, 300 sec: 3957.1). Total num frames: 3551232. Throughput: 0: 1027.8. Samples: 887024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 01:04:29,969][01536] Avg episode reward: [(0, '18.876')] [2024-12-28 01:04:33,838][03572] Updated weights for policy 0, policy_version 870 (0.0029) [2024-12-28 01:04:34,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3567616. Throughput: 0: 970.4. Samples: 891662. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 01:04:34,965][01536] Avg episode reward: [(0, '19.672')] [2024-12-28 01:04:39,963][01536] Fps is (10 sec: 4096.4, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 3592192. Throughput: 0: 972.8. Samples: 895280. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:04:39,966][01536] Avg episode reward: [(0, '18.238')] [2024-12-28 01:04:39,979][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000877_3592192.pth... [2024-12-28 01:04:40,123][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000645_2641920.pth [2024-12-28 01:04:42,436][03572] Updated weights for policy 0, policy_version 880 (0.0031) [2024-12-28 01:04:44,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 3612672. Throughput: 0: 1034.4. Samples: 902378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:04:44,974][01536] Avg episode reward: [(0, '18.096')] [2024-12-28 01:04:49,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3943.4). Total num frames: 3624960. Throughput: 0: 982.6. Samples: 906718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:04:49,966][01536] Avg episode reward: [(0, '19.112')] [2024-12-28 01:04:53,729][03572] Updated weights for policy 0, policy_version 890 (0.0036) [2024-12-28 01:04:54,963][01536] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 3649536. Throughput: 0: 973.0. Samples: 909854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:04:54,966][01536] Avg episode reward: [(0, '18.769')] [2024-12-28 01:04:59,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 3971.0). Total num frames: 3674112. Throughput: 0: 1019.1. Samples: 917084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:04:59,966][01536] Avg episode reward: [(0, '19.142')] [2024-12-28 01:05:03,946][03572] Updated weights for policy 0, policy_version 900 (0.0014) [2024-12-28 01:05:04,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3686400. Throughput: 0: 1002.2. Samples: 922274. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:05:04,965][01536] Avg episode reward: [(0, '19.421')] [2024-12-28 01:05:09,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3706880. Throughput: 0: 969.5. Samples: 924442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:05:09,970][01536] Avg episode reward: [(0, '20.243')] [2024-12-28 01:05:09,980][03555] Saving new best policy, reward=20.243! [2024-12-28 01:05:13,737][03572] Updated weights for policy 0, policy_version 910 (0.0028) [2024-12-28 01:05:14,963][01536] Fps is (10 sec: 4505.5, 60 sec: 4096.1, 300 sec: 3971.0). Total num frames: 3731456. Throughput: 0: 989.4. Samples: 931546. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:05:14,965][01536] Avg episode reward: [(0, '19.910')] [2024-12-28 01:05:19,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 3751936. Throughput: 0: 1028.8. Samples: 937958. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 01:05:19,968][01536] Avg episode reward: [(0, '19.574')] [2024-12-28 01:05:24,963][01536] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 3764224. Throughput: 0: 995.3. Samples: 940070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:05:24,971][01536] Avg episode reward: [(0, '19.672')] [2024-12-28 01:05:25,109][03572] Updated weights for policy 0, policy_version 920 (0.0016) [2024-12-28 01:05:29,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 3788800. Throughput: 0: 974.9. Samples: 946248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:05:29,967][01536] Avg episode reward: [(0, '17.512')] [2024-12-28 01:05:33,534][03572] Updated weights for policy 0, policy_version 930 (0.0022) [2024-12-28 01:05:34,963][01536] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 3813376. Throughput: 0: 1037.1. Samples: 953386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:05:34,965][01536] Avg episode reward: [(0, '16.675')] [2024-12-28 01:05:39,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3825664. Throughput: 0: 1018.1. Samples: 955668. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-12-28 01:05:39,967][01536] Avg episode reward: [(0, '17.337')] [2024-12-28 01:05:44,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 3846144. Throughput: 0: 972.4. Samples: 960840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:05:44,966][01536] Avg episode reward: [(0, '18.080')] [2024-12-28 01:05:45,004][03572] Updated weights for policy 0, policy_version 940 (0.0029) [2024-12-28 01:05:49,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 3870720. Throughput: 0: 1018.3. Samples: 968098. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:05:49,969][01536] Avg episode reward: [(0, '18.183')] [2024-12-28 01:05:54,947][03572] Updated weights for policy 0, policy_version 950 (0.0023) [2024-12-28 01:05:54,963][01536] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 3891200. Throughput: 0: 1042.5. Samples: 971354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2024-12-28 01:05:54,974][01536] Avg episode reward: [(0, '18.858')] [2024-12-28 01:05:59,963][01536] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3957.1). Total num frames: 3907584. Throughput: 0: 980.4. Samples: 975666. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) [2024-12-28 01:05:59,970][01536] Avg episode reward: [(0, '19.230')] [2024-12-28 01:06:04,832][03572] Updated weights for policy 0, policy_version 960 (0.0021) [2024-12-28 01:06:04,963][01536] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3984.9). Total num frames: 3932160. Throughput: 0: 993.8. Samples: 982680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2024-12-28 01:06:04,965][01536] Avg episode reward: [(0, '20.313')] [2024-12-28 01:06:04,970][03555] Saving new best policy, reward=20.313! [2024-12-28 01:06:09,963][01536] Fps is (10 sec: 4505.8, 60 sec: 4096.0, 300 sec: 3971.0). Total num frames: 3952640. Throughput: 0: 1025.0. Samples: 986196. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) [2024-12-28 01:06:09,966][01536] Avg episode reward: [(0, '20.822')] [2024-12-28 01:06:09,985][03555] Saving new best policy, reward=20.822! [2024-12-28 01:06:14,963][01536] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3964928. Throughput: 0: 993.3. Samples: 990946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-12-28 01:06:14,970][01536] Avg episode reward: [(0, '21.269')] [2024-12-28 01:06:14,974][03555] Saving new best policy, reward=21.269! [2024-12-28 01:06:16,335][03572] Updated weights for policy 0, policy_version 970 (0.0030) [2024-12-28 01:06:19,963][01536] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.1). Total num frames: 3989504. Throughput: 0: 969.0. Samples: 996990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2024-12-28 01:06:19,970][01536] Avg episode reward: [(0, '21.145')] [2024-12-28 01:06:23,302][03555] Stopping Batcher_0... [2024-12-28 01:06:23,302][03555] Loop batcher_evt_loop terminating... [2024-12-28 01:06:23,304][01536] Component Batcher_0 stopped! [2024-12-28 01:06:23,312][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-12-28 01:06:23,360][03572] Weights refcount: 2 0 [2024-12-28 01:06:23,365][01536] Component InferenceWorker_p0-w0 stopped! [2024-12-28 01:06:23,372][03572] Stopping InferenceWorker_p0-w0... [2024-12-28 01:06:23,373][03572] Loop inference_proc0-0_evt_loop terminating... [2024-12-28 01:06:23,462][03555] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000760_3112960.pth [2024-12-28 01:06:23,477][03555] Saving new best policy, reward=23.003! [2024-12-28 01:06:23,614][03555] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-12-28 01:06:23,746][03573] Stopping RolloutWorker_w0... [2024-12-28 01:06:23,747][01536] Component RolloutWorker_w0 stopped! [2024-12-28 01:06:23,787][03555] Stopping LearnerWorker_p0... [2024-12-28 01:06:23,792][03573] Loop rollout_proc0_evt_loop terminating... [2024-12-28 01:06:23,797][03575] Stopping RolloutWorker_w2... [2024-12-28 01:06:23,788][01536] Component LearnerWorker_p0 stopped! [2024-12-28 01:06:23,790][03555] Loop learner_proc0_evt_loop terminating... [2024-12-28 01:06:23,800][01536] Component RolloutWorker_w2 stopped! [2024-12-28 01:06:23,800][03577] Stopping RolloutWorker_w4... [2024-12-28 01:06:23,802][01536] Component RolloutWorker_w4 stopped! [2024-12-28 01:06:23,815][01536] Component RolloutWorker_w6 stopped! [2024-12-28 01:06:23,815][03578] Stopping RolloutWorker_w6... [2024-12-28 01:06:23,798][03575] Loop rollout_proc2_evt_loop terminating... [2024-12-28 01:06:23,811][03577] Loop rollout_proc4_evt_loop terminating... [2024-12-28 01:06:23,820][03578] Loop rollout_proc6_evt_loop terminating... [2024-12-28 01:06:23,918][01536] Component RolloutWorker_w7 stopped! [2024-12-28 01:06:23,929][01536] Component RolloutWorker_w5 stopped! [2024-12-28 01:06:23,934][03579] Stopping RolloutWorker_w5... [2024-12-28 01:06:23,935][03579] Loop rollout_proc5_evt_loop terminating... [2024-12-28 01:06:23,925][03580] Stopping RolloutWorker_w7... [2024-12-28 01:06:23,936][03580] Loop rollout_proc7_evt_loop terminating... [2024-12-28 01:06:23,943][01536] Component RolloutWorker_w3 stopped! [2024-12-28 01:06:23,947][03576] Stopping RolloutWorker_w3... [2024-12-28 01:06:23,948][03576] Loop rollout_proc3_evt_loop terminating... [2024-12-28 01:06:23,950][01536] Component RolloutWorker_w1 stopped! [2024-12-28 01:06:23,954][01536] Waiting for process learner_proc0 to stop... [2024-12-28 01:06:23,958][03574] Stopping RolloutWorker_w1... [2024-12-28 01:06:23,959][03574] Loop rollout_proc1_evt_loop terminating... [2024-12-28 01:06:25,503][01536] Waiting for process inference_proc0-0 to join... [2024-12-28 01:06:25,506][01536] Waiting for process rollout_proc0 to join... [2024-12-28 01:06:28,401][01536] Waiting for process rollout_proc1 to join... [2024-12-28 01:06:28,405][01536] Waiting for process rollout_proc2 to join... [2024-12-28 01:06:28,409][01536] Waiting for process rollout_proc3 to join... [2024-12-28 01:06:28,413][01536] Waiting for process rollout_proc4 to join... [2024-12-28 01:06:28,419][01536] Waiting for process rollout_proc5 to join... [2024-12-28 01:06:28,421][01536] Waiting for process rollout_proc6 to join... [2024-12-28 01:06:28,426][01536] Waiting for process rollout_proc7 to join... [2024-12-28 01:06:28,432][01536] Batcher 0 profile tree view: batching: 25.7276, releasing_batches: 0.0279 [2024-12-28 01:06:28,433][01536] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 401.7001 update_model: 8.7034 weight_update: 0.0016 one_step: 0.0121 handle_policy_step: 575.4089 deserialize: 14.5684, stack: 3.2220, obs_to_device_normalize: 122.0526, forward: 287.9411, send_messages: 28.7459 prepare_outputs: 90.0485 to_cpu: 54.6229 [2024-12-28 01:06:28,434][01536] Learner 0 profile tree view: misc: 0.0054, prepare_batch: 13.3251 train: 74.1783 epoch_init: 0.0054, minibatch_init: 0.0085, losses_postprocess: 0.7476, kl_divergence: 0.6260, after_optimizer: 33.5690 calculate_losses: 26.6811 losses_init: 0.0034, forward_head: 1.2182, bptt_initial: 17.8669, tail: 1.1152, advantages_returns: 0.3500, losses: 3.9138 bptt: 1.9229 bptt_forward_core: 1.8310 update: 11.8814 clip: 0.8814 [2024-12-28 01:06:28,436][01536] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.3278, enqueue_policy_requests: 95.1229, env_step: 806.7277, overhead: 12.3378, complete_rollouts: 7.1612 save_policy_outputs: 19.6764 split_output_tensors: 7.7918 [2024-12-28 01:06:28,437][01536] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.3041, enqueue_policy_requests: 96.2076, env_step: 804.9972, overhead: 12.0463, complete_rollouts: 6.1050 save_policy_outputs: 20.0061 split_output_tensors: 7.9358 [2024-12-28 01:06:28,442][01536] Loop Runner_EvtLoop terminating... [2024-12-28 01:06:28,443][01536] Runner profile tree view: main_loop: 1059.0170 [2024-12-28 01:06:28,444][01536] Collected {0: 4005888}, FPS: 3782.6 [2024-12-28 01:06:28,969][01536] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2024-12-28 01:06:28,970][01536] Overriding arg 'num_workers' with value 1 passed from command line [2024-12-28 01:06:28,973][01536] Adding new argument 'no_render'=True that is not in the saved config file! [2024-12-28 01:06:28,976][01536] Adding new argument 'save_video'=True that is not in the saved config file! [2024-12-28 01:06:28,978][01536] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-12-28 01:06:28,980][01536] Adding new argument 'video_name'=None that is not in the saved config file! [2024-12-28 01:06:28,982][01536] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2024-12-28 01:06:28,985][01536] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-12-28 01:06:28,986][01536] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2024-12-28 01:06:28,990][01536] Adding new argument 'hf_repository'=None that is not in the saved config file! [2024-12-28 01:06:28,991][01536] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-12-28 01:06:28,994][01536] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-12-28 01:06:28,995][01536] Adding new argument 'train_script'=None that is not in the saved config file! [2024-12-28 01:06:28,997][01536] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-12-28 01:06:28,998][01536] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-12-28 01:06:29,031][01536] Doom resolution: 160x120, resize resolution: (128, 72) [2024-12-28 01:06:29,036][01536] RunningMeanStd input shape: (3, 72, 128) [2024-12-28 01:06:29,038][01536] RunningMeanStd input shape: (1,) [2024-12-28 01:06:29,057][01536] ConvEncoder: input_channels=3 [2024-12-28 01:06:29,163][01536] Conv encoder output size: 512 [2024-12-28 01:06:29,165][01536] Policy head output size: 512 [2024-12-28 01:06:29,434][01536] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-12-28 01:06:30,245][01536] Num frames 100... [2024-12-28 01:06:30,364][01536] Num frames 200... [2024-12-28 01:06:30,511][01536] Num frames 300... [2024-12-28 01:06:30,634][01536] Num frames 400... [2024-12-28 01:06:30,756][01536] Num frames 500... [2024-12-28 01:06:30,878][01536] Num frames 600... [2024-12-28 01:06:31,005][01536] Num frames 700... [2024-12-28 01:06:31,127][01536] Num frames 800... [2024-12-28 01:06:31,248][01536] Num frames 900... [2024-12-28 01:06:31,369][01536] Num frames 1000... [2024-12-28 01:06:31,493][01536] Num frames 1100... [2024-12-28 01:06:31,627][01536] Num frames 1200... [2024-12-28 01:06:31,750][01536] Num frames 1300... [2024-12-28 01:06:31,874][01536] Num frames 1400... [2024-12-28 01:06:31,977][01536] Avg episode rewards: #0: 38.400, true rewards: #0: 14.400 [2024-12-28 01:06:31,980][01536] Avg episode reward: 38.400, avg true_objective: 14.400 [2024-12-28 01:06:32,054][01536] Num frames 1500... [2024-12-28 01:06:32,175][01536] Num frames 1600... [2024-12-28 01:06:32,295][01536] Num frames 1700... [2024-12-28 01:06:32,416][01536] Num frames 1800... [2024-12-28 01:06:32,553][01536] Num frames 1900... [2024-12-28 01:06:32,673][01536] Num frames 2000... [2024-12-28 01:06:32,798][01536] Num frames 2100... [2024-12-28 01:06:32,919][01536] Num frames 2200... [2024-12-28 01:06:32,994][01536] Avg episode rewards: #0: 26.580, true rewards: #0: 11.080 [2024-12-28 01:06:32,996][01536] Avg episode reward: 26.580, avg true_objective: 11.080 [2024-12-28 01:06:33,102][01536] Num frames 2300... [2024-12-28 01:06:33,245][01536] Num frames 2400... [2024-12-28 01:06:33,375][01536] Num frames 2500... [2024-12-28 01:06:33,501][01536] Num frames 2600... [2024-12-28 01:06:33,635][01536] Num frames 2700... [2024-12-28 01:06:33,760][01536] Num frames 2800... [2024-12-28 01:06:33,882][01536] Num frames 2900... [2024-12-28 01:06:34,008][01536] Num frames 3000... [2024-12-28 01:06:34,131][01536] Num frames 3100... [2024-12-28 01:06:34,255][01536] Num frames 3200... [2024-12-28 01:06:34,373][01536] Num frames 3300... [2024-12-28 01:06:34,498][01536] Num frames 3400... [2024-12-28 01:06:34,636][01536] Num frames 3500... [2024-12-28 01:06:34,753][01536] Num frames 3600... [2024-12-28 01:06:34,874][01536] Avg episode rewards: #0: 28.520, true rewards: #0: 12.187 [2024-12-28 01:06:34,875][01536] Avg episode reward: 28.520, avg true_objective: 12.187 [2024-12-28 01:06:34,931][01536] Num frames 3700... [2024-12-28 01:06:35,049][01536] Num frames 3800... [2024-12-28 01:06:35,168][01536] Num frames 3900... [2024-12-28 01:06:35,291][01536] Num frames 4000... [2024-12-28 01:06:35,408][01536] Num frames 4100... [2024-12-28 01:06:35,538][01536] Num frames 4200... [2024-12-28 01:06:35,665][01536] Num frames 4300... [2024-12-28 01:06:35,786][01536] Num frames 4400... [2024-12-28 01:06:35,908][01536] Num frames 4500... [2024-12-28 01:06:35,977][01536] Avg episode rewards: #0: 25.775, true rewards: #0: 11.275 [2024-12-28 01:06:35,978][01536] Avg episode reward: 25.775, avg true_objective: 11.275 [2024-12-28 01:06:36,087][01536] Num frames 4600... [2024-12-28 01:06:36,207][01536] Num frames 4700... [2024-12-28 01:06:36,326][01536] Num frames 4800... [2024-12-28 01:06:36,443][01536] Num frames 4900... [2024-12-28 01:06:36,572][01536] Num frames 5000... [2024-12-28 01:06:36,702][01536] Num frames 5100... [2024-12-28 01:06:36,823][01536] Num frames 5200... [2024-12-28 01:06:36,947][01536] Num frames 5300... [2024-12-28 01:06:37,057][01536] Avg episode rewards: #0: 24.084, true rewards: #0: 10.684 [2024-12-28 01:06:37,058][01536] Avg episode reward: 24.084, avg true_objective: 10.684 [2024-12-28 01:06:37,130][01536] Num frames 5400... [2024-12-28 01:06:37,258][01536] Num frames 5500... [2024-12-28 01:06:37,376][01536] Num frames 5600... [2024-12-28 01:06:37,501][01536] Num frames 5700... [2024-12-28 01:06:37,626][01536] Num frames 5800... [2024-12-28 01:06:37,753][01536] Num frames 5900... [2024-12-28 01:06:37,877][01536] Num frames 6000... [2024-12-28 01:06:38,047][01536] Avg episode rewards: #0: 22.488, true rewards: #0: 10.155 [2024-12-28 01:06:38,048][01536] Avg episode reward: 22.488, avg true_objective: 10.155 [2024-12-28 01:06:38,059][01536] Num frames 6100... [2024-12-28 01:06:38,181][01536] Num frames 6200... [2024-12-28 01:06:38,302][01536] Num frames 6300... [2024-12-28 01:06:38,420][01536] Num frames 6400... [2024-12-28 01:06:38,495][01536] Avg episode rewards: #0: 20.162, true rewards: #0: 9.161 [2024-12-28 01:06:38,496][01536] Avg episode reward: 20.162, avg true_objective: 9.161 [2024-12-28 01:06:38,604][01536] Num frames 6500... [2024-12-28 01:06:38,730][01536] Num frames 6600... [2024-12-28 01:06:38,870][01536] Num frames 6700... [2024-12-28 01:06:39,038][01536] Num frames 6800... [2024-12-28 01:06:39,203][01536] Num frames 6900... [2024-12-28 01:06:39,353][01536] Avg episode rewards: #0: 18.571, true rewards: #0: 8.696 [2024-12-28 01:06:39,355][01536] Avg episode reward: 18.571, avg true_objective: 8.696 [2024-12-28 01:06:39,430][01536] Num frames 7000... [2024-12-28 01:06:39,597][01536] Num frames 7100... [2024-12-28 01:06:39,771][01536] Num frames 7200... [2024-12-28 01:06:39,932][01536] Num frames 7300... [2024-12-28 01:06:40,102][01536] Num frames 7400... [2024-12-28 01:06:40,271][01536] Num frames 7500... [2024-12-28 01:06:40,443][01536] Num frames 7600... [2024-12-28 01:06:40,611][01536] Num frames 7700... [2024-12-28 01:06:40,779][01536] Num frames 7800... [2024-12-28 01:06:40,963][01536] Num frames 7900... [2024-12-28 01:06:41,134][01536] Num frames 8000... [2024-12-28 01:06:41,312][01536] Num frames 8100... [2024-12-28 01:06:41,513][01536] Avg episode rewards: #0: 19.663, true rewards: #0: 9.108 [2024-12-28 01:06:41,514][01536] Avg episode reward: 19.663, avg true_objective: 9.108 [2024-12-28 01:06:41,521][01536] Num frames 8200... [2024-12-28 01:06:41,643][01536] Num frames 8300... [2024-12-28 01:06:41,764][01536] Num frames 8400... [2024-12-28 01:06:41,893][01536] Num frames 8500... [2024-12-28 01:06:42,014][01536] Num frames 8600... [2024-12-28 01:06:42,135][01536] Num frames 8700... [2024-12-28 01:06:42,255][01536] Num frames 8800... [2024-12-28 01:06:42,377][01536] Num frames 8900... [2024-12-28 01:06:42,507][01536] Num frames 9000... [2024-12-28 01:06:42,627][01536] Num frames 9100... [2024-12-28 01:06:42,748][01536] Num frames 9200... [2024-12-28 01:06:42,874][01536] Num frames 9300... [2024-12-28 01:06:42,999][01536] Num frames 9400... [2024-12-28 01:06:43,121][01536] Num frames 9500... [2024-12-28 01:06:43,246][01536] Num frames 9600... [2024-12-28 01:06:43,366][01536] Num frames 9700... [2024-12-28 01:06:43,490][01536] Num frames 9800... [2024-12-28 01:06:43,624][01536] Avg episode rewards: #0: 21.261, true rewards: #0: 9.861 [2024-12-28 01:06:43,627][01536] Avg episode reward: 21.261, avg true_objective: 9.861 [2024-12-28 01:07:38,730][01536] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2024-12-28 01:10:41,517][01536] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2024-12-28 01:10:41,519][01536] Overriding arg 'num_workers' with value 1 passed from command line [2024-12-28 01:10:41,521][01536] Adding new argument 'no_render'=True that is not in the saved config file! [2024-12-28 01:10:41,523][01536] Adding new argument 'save_video'=True that is not in the saved config file! [2024-12-28 01:10:41,524][01536] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-12-28 01:10:41,526][01536] Adding new argument 'video_name'=None that is not in the saved config file! [2024-12-28 01:10:41,527][01536] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2024-12-28 01:10:41,528][01536] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-12-28 01:10:41,530][01536] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2024-12-28 01:10:41,531][01536] Adding new argument 'hf_repository'='TPK-MAKG/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2024-12-28 01:10:41,532][01536] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-12-28 01:10:41,533][01536] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-12-28 01:10:41,534][01536] Adding new argument 'train_script'=None that is not in the saved config file! [2024-12-28 01:10:41,535][01536] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-12-28 01:10:41,536][01536] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-12-28 01:10:41,565][01536] RunningMeanStd input shape: (3, 72, 128) [2024-12-28 01:10:41,567][01536] RunningMeanStd input shape: (1,) [2024-12-28 01:10:41,579][01536] ConvEncoder: input_channels=3 [2024-12-28 01:10:41,616][01536] Conv encoder output size: 512 [2024-12-28 01:10:41,617][01536] Policy head output size: 512 [2024-12-28 01:10:41,636][01536] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-12-28 01:10:42,047][01536] Num frames 100... [2024-12-28 01:10:42,166][01536] Num frames 200... [2024-12-28 01:10:42,291][01536] Num frames 300... [2024-12-28 01:10:42,416][01536] Num frames 400... [2024-12-28 01:10:42,568][01536] Num frames 500... [2024-12-28 01:10:42,697][01536] Num frames 600... [2024-12-28 01:10:42,815][01536] Num frames 700... [2024-12-28 01:10:42,957][01536] Avg episode rewards: #0: 14.680, true rewards: #0: 7.680 [2024-12-28 01:10:42,960][01536] Avg episode reward: 14.680, avg true_objective: 7.680 [2024-12-28 01:10:42,999][01536] Num frames 800... [2024-12-28 01:10:43,128][01536] Num frames 900... [2024-12-28 01:10:43,256][01536] Num frames 1000... [2024-12-28 01:10:43,379][01536] Num frames 1100... [2024-12-28 01:10:43,507][01536] Num frames 1200... [2024-12-28 01:10:43,623][01536] Num frames 1300... [2024-12-28 01:10:43,740][01536] Num frames 1400... [2024-12-28 01:10:43,866][01536] Num frames 1500... [2024-12-28 01:10:43,928][01536] Avg episode rewards: #0: 14.520, true rewards: #0: 7.520 [2024-12-28 01:10:43,931][01536] Avg episode reward: 14.520, avg true_objective: 7.520 [2024-12-28 01:10:44,052][01536] Num frames 1600... [2024-12-28 01:10:44,171][01536] Num frames 1700... [2024-12-28 01:10:44,289][01536] Num frames 1800... [2024-12-28 01:10:44,412][01536] Num frames 1900... [2024-12-28 01:10:44,543][01536] Num frames 2000... [2024-12-28 01:10:44,661][01536] Num frames 2100... [2024-12-28 01:10:44,780][01536] Num frames 2200... [2024-12-28 01:10:44,899][01536] Num frames 2300... [2024-12-28 01:10:45,020][01536] Num frames 2400... [2024-12-28 01:10:45,150][01536] Num frames 2500... [2024-12-28 01:10:45,269][01536] Num frames 2600... [2024-12-28 01:10:45,387][01536] Num frames 2700... [2024-12-28 01:10:45,515][01536] Num frames 2800... [2024-12-28 01:10:45,636][01536] Num frames 2900... [2024-12-28 01:10:45,779][01536] Avg episode rewards: #0: 22.237, true rewards: #0: 9.903 [2024-12-28 01:10:45,781][01536] Avg episode reward: 22.237, avg true_objective: 9.903 [2024-12-28 01:10:45,818][01536] Num frames 3000... [2024-12-28 01:10:45,936][01536] Num frames 3100... [2024-12-28 01:10:46,055][01536] Num frames 3200... [2024-12-28 01:10:46,181][01536] Num frames 3300... [2024-12-28 01:10:46,338][01536] Avg episode rewards: #0: 18.218, true rewards: #0: 8.467 [2024-12-28 01:10:46,341][01536] Avg episode reward: 18.218, avg true_objective: 8.467 [2024-12-28 01:10:46,361][01536] Num frames 3400... [2024-12-28 01:10:46,482][01536] Num frames 3500... [2024-12-28 01:10:46,607][01536] Num frames 3600... [2024-12-28 01:10:46,731][01536] Num frames 3700... [2024-12-28 01:10:46,855][01536] Num frames 3800... [2024-12-28 01:10:47,021][01536] Num frames 3900... [2024-12-28 01:10:47,198][01536] Num frames 4000... [2024-12-28 01:10:47,361][01536] Num frames 4100... [2024-12-28 01:10:47,534][01536] Num frames 4200... [2024-12-28 01:10:47,695][01536] Num frames 4300... [2024-12-28 01:10:47,857][01536] Num frames 4400... [2024-12-28 01:10:48,020][01536] Num frames 4500... [2024-12-28 01:10:48,192][01536] Num frames 4600... [2024-12-28 01:10:48,364][01536] Num frames 4700... [2024-12-28 01:10:48,547][01536] Num frames 4800... [2024-12-28 01:10:48,736][01536] Avg episode rewards: #0: 21.758, true rewards: #0: 9.758 [2024-12-28 01:10:48,738][01536] Avg episode reward: 21.758, avg true_objective: 9.758 [2024-12-28 01:10:48,778][01536] Num frames 4900... [2024-12-28 01:10:48,950][01536] Num frames 5000... [2024-12-28 01:10:49,123][01536] Num frames 5100... [2024-12-28 01:10:49,300][01536] Num frames 5200... [2024-12-28 01:10:49,461][01536] Num frames 5300... [2024-12-28 01:10:49,596][01536] Num frames 5400... [2024-12-28 01:10:49,717][01536] Num frames 5500... [2024-12-28 01:10:49,847][01536] Num frames 5600... [2024-12-28 01:10:49,968][01536] Num frames 5700... [2024-12-28 01:10:50,088][01536] Num frames 5800... [2024-12-28 01:10:50,209][01536] Num frames 5900... [2024-12-28 01:10:50,318][01536] Avg episode rewards: #0: 21.892, true rewards: #0: 9.892 [2024-12-28 01:10:50,320][01536] Avg episode reward: 21.892, avg true_objective: 9.892 [2024-12-28 01:10:50,399][01536] Num frames 6000... [2024-12-28 01:10:50,533][01536] Num frames 6100... [2024-12-28 01:10:50,655][01536] Num frames 6200... [2024-12-28 01:10:50,779][01536] Num frames 6300... [2024-12-28 01:10:50,899][01536] Num frames 6400... [2024-12-28 01:10:51,023][01536] Num frames 6500... [2024-12-28 01:10:51,145][01536] Num frames 6600... [2024-12-28 01:10:51,266][01536] Num frames 6700... [2024-12-28 01:10:51,359][01536] Avg episode rewards: #0: 21.319, true rewards: #0: 9.604 [2024-12-28 01:10:51,361][01536] Avg episode reward: 21.319, avg true_objective: 9.604 [2024-12-28 01:10:51,453][01536] Num frames 6800... [2024-12-28 01:10:51,587][01536] Num frames 6900... [2024-12-28 01:10:51,710][01536] Num frames 7000... [2024-12-28 01:10:51,831][01536] Num frames 7100... [2024-12-28 01:10:51,952][01536] Num frames 7200... [2024-12-28 01:10:52,073][01536] Num frames 7300... [2024-12-28 01:10:52,197][01536] Num frames 7400... [2024-12-28 01:10:52,325][01536] Num frames 7500... [2024-12-28 01:10:52,446][01536] Num frames 7600... [2024-12-28 01:10:52,577][01536] Num frames 7700... [2024-12-28 01:10:52,702][01536] Num frames 7800... [2024-12-28 01:10:52,828][01536] Num frames 7900... [2024-12-28 01:10:52,948][01536] Num frames 8000... [2024-12-28 01:10:53,078][01536] Num frames 8100... [2024-12-28 01:10:53,203][01536] Num frames 8200... [2024-12-28 01:10:53,292][01536] Avg episode rewards: #0: 23.409, true rewards: #0: 10.284 [2024-12-28 01:10:53,294][01536] Avg episode reward: 23.409, avg true_objective: 10.284 [2024-12-28 01:10:53,390][01536] Num frames 8300... [2024-12-28 01:10:53,526][01536] Num frames 8400... [2024-12-28 01:10:53,648][01536] Num frames 8500... [2024-12-28 01:10:53,768][01536] Num frames 8600... [2024-12-28 01:10:53,891][01536] Num frames 8700... [2024-12-28 01:10:54,014][01536] Num frames 8800... [2024-12-28 01:10:54,176][01536] Avg episode rewards: #0: 22.429, true rewards: #0: 9.873 [2024-12-28 01:10:54,178][01536] Avg episode reward: 22.429, avg true_objective: 9.873 [2024-12-28 01:10:54,199][01536] Num frames 8900... [2024-12-28 01:10:54,317][01536] Num frames 9000... [2024-12-28 01:10:54,448][01536] Num frames 9100... [2024-12-28 01:10:54,576][01536] Num frames 9200... [2024-12-28 01:10:54,700][01536] Num frames 9300... [2024-12-28 01:10:54,823][01536] Num frames 9400... [2024-12-28 01:10:54,945][01536] Num frames 9500... [2024-12-28 01:10:55,073][01536] Num frames 9600... [2024-12-28 01:10:55,157][01536] Avg episode rewards: #0: 21.722, true rewards: #0: 9.622 [2024-12-28 01:10:55,158][01536] Avg episode reward: 21.722, avg true_objective: 9.622 [2024-12-28 01:11:48,975][01536] Replay video saved to /content/train_dir/default_experiment/replay.mp4!