{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9905679821968079, "min": 0.9905679821968079, "max": 2.870112419128418, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9479.7353515625, "min": 9479.7353515625, "max": 29392.8203125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.542269706726074, "min": 0.436093270778656, "max": 12.641898155212402, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2445.74267578125, "min": 84.60209655761719, "max": 2578.947265625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06483898489372508, "min": 0.06352636912976653, "max": 0.07632039742772986, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25935593957490033, "min": 0.2541054765190661, "max": 0.37813210600242936, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21808049170409932, "min": 0.1486261908556152, "max": 0.2853587735517352, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8723219668163973, "min": 0.5945047634224608, "max": 1.426793867758676, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.25, "min": 3.659090909090909, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1067.0, "min": 161.0, "max": 1371.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.25, "min": 3.659090909090909, "max": 25.136363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1067.0, "min": 161.0, "max": 1371.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1695394432", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695394901" }, "total": 468.565025098, "count": 1, "self": 0.4315352239996173, "children": { "run_training.setup": { "total": 0.04176162900012059, "count": 1, "self": 0.04176162900012059 }, "TrainerController.start_learning": { "total": 468.09172824500024, "count": 1, "self": 0.514204477987505, "children": { "TrainerController._reset_env": { "total": 5.107928096000023, "count": 1, "self": 5.107928096000023 }, "TrainerController.advance": { "total": 462.3062296520127, "count": 18204, "self": 0.259350869028367, "children": { "env_step": { "total": 462.0468787829843, "count": 18204, "self": 335.5412605870131, "children": { "SubprocessEnvManager._take_step": { "total": 126.23264098198888, "count": 18204, "self": 1.7489456039616016, "children": { "TorchPolicy.evaluate": { "total": 124.48369537802728, "count": 18204, "self": 124.48369537802728 } } }, "workers": { "total": 0.2729772139823581, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 466.533233262963, "count": 18204, "is_parallel": true, "self": 221.27764433995458, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005599847999974372, "count": 1, "is_parallel": true, "self": 0.003952773999799319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016470740001750528, "count": 10, "is_parallel": true, "self": 0.0016470740001750528 } } }, "UnityEnvironment.step": { "total": 0.07310378800002582, "count": 1, "is_parallel": true, "self": 0.0006380299998909322, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004580760000862938, "count": 1, "is_parallel": true, "self": 0.0004580760000862938 }, "communicator.exchange": { "total": 0.0655762330000016, "count": 1, "is_parallel": true, "self": 0.0655762330000016 }, "steps_from_proto": { "total": 0.006431449000046996, "count": 1, "is_parallel": true, "self": 0.0004294929995012353, "children": { "_process_rank_one_or_two_observation": { "total": 0.006001956000545761, "count": 10, "is_parallel": true, "self": 0.006001956000545761 } } } } } } }, "UnityEnvironment.step": { "total": 245.25558892300842, "count": 18203, "is_parallel": true, "self": 10.398779897999475, "children": { "UnityEnvironment._generate_step_input": { "total": 5.246553642999743, "count": 18203, "is_parallel": true, "self": 5.246553642999743 }, "communicator.exchange": { "total": 193.51584178901112, "count": 18203, "is_parallel": true, "self": 193.51584178901112 }, "steps_from_proto": { "total": 36.09441359299808, "count": 18203, "is_parallel": true, "self": 6.484813412918129, "children": { "_process_rank_one_or_two_observation": { "total": 29.60960018007995, "count": 182030, "is_parallel": true, "self": 29.60960018007995 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017802000002120622, "count": 1, "self": 0.00017802000002120622, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 458.7752014971038, "count": 437497, "is_parallel": true, "self": 9.64992278710929, "children": { "process_trajectory": { "total": 250.02878089399564, "count": 437497, "is_parallel": true, "self": 249.2222624149956, "children": { "RLTrainer._checkpoint": { "total": 0.806518479000033, "count": 4, "is_parallel": true, "self": 0.806518479000033 } } }, "_update_policy": { "total": 199.09649781599887, "count": 90, "is_parallel": true, "self": 79.48694423101233, "children": { "TorchPPOOptimizer.update": { "total": 119.60955358498654, "count": 4584, "is_parallel": true, "self": 119.60955358498654 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16318799900000158, "count": 1, "self": 0.0008954439999797614, "children": { "RLTrainer._checkpoint": { "total": 0.16229255500002182, "count": 1, "self": 0.16229255500002182 } } } } } } }