{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9509430527687073, "min": 0.9332674741744995, "max": 1.0425547361373901, "count": 7 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9675.845703125, "min": 8900.787109375, "max": 10665.3349609375, "count": 7 }, "SnowballTarget.Step.mean": { "value": 269976.0, "min": 209936.0, "max": 269976.0, "count": 7 }, "SnowballTarget.Step.sum": { "value": 269976.0, "min": 209936.0, "max": 269976.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.233717918395996, "min": 12.270806312561035, "max": 13.233717918395996, "count": 7 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2580.574951171875, "min": 2355.994873046875, "max": 2664.337890625, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 7 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06434979716241108, "min": 0.06434979716241108, "max": 0.07744694704314872, "count": 7 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25739918864964434, "min": 0.25739918864964434, "max": 0.3872347352157436, "count": 7 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17866915223353047, "min": 0.17456258690970783, "max": 0.19856594356836058, "count": 7 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7146766089341219, "min": 0.6982503476388313, "max": 0.9928297178418029, "count": 7 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00014104565298479998, "min": 0.00014104565298479998, "max": 0.00017668564110480002, "count": 7 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0005641826119391999, "min": 0.0005641826119391999, "max": 0.000853728215424, "count": 7 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1470152, "min": 0.1470152, "max": 0.15889520000000001, "count": 7 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5880608, "min": 0.5880608, "max": 0.7845760000000002, "count": 7 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00235605848, "min": 0.00235605848, "max": 0.002948870480000001, "count": 7 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00942423392, "min": 0.00942423392, "max": 0.0142503424, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.954545454545453, "min": 23.818181818181817, "max": 25.954545454545453, "count": 7 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 1048.0, "max": 1411.0, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 23.818181818181817, "max": 25.954545454545453, "count": 7 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 1048.0, "max": 1411.0, "count": 7 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 7 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696418834", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo.yaml --resume --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": "1696419045" }, "total": 211.43181110000023, "count": 1, "self": 0.008607448000020668, "children": { "run_training.setup": { "total": 0.04204078000020672, "count": 1, "self": 0.04204078000020672 }, "TrainerController.start_learning": { "total": 211.381162872, "count": 1, "self": 0.8524889690129385, "children": { "TrainerController._reset_env": { "total": 4.148062613000093, "count": 1, "self": 4.148062613000093 }, "TrainerController.advance": { "total": 206.06741542598684, "count": 7264, "self": 0.12974490201804656, "children": { "env_step": { "total": 205.9376705239688, "count": 7264, "self": 150.14040884797123, "children": { "SubprocessEnvManager._take_step": { "total": 55.66749211900424, "count": 7264, "self": 0.7677587529815355, "children": { "TorchPolicy.evaluate": { "total": 54.8997333660227, "count": 7264, "self": 54.8997333660227 } } }, "workers": { "total": 0.12976955699332393, "count": 7264, "self": 0.0, "children": { "worker_root": { "total": 209.2923571470028, "count": 7264, "is_parallel": true, "self": 99.49096950098556, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002168768000046839, "count": 1, "is_parallel": true, "self": 0.0006789990002289414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014897689998178976, "count": 10, "is_parallel": true, "self": 0.0014897689998178976 } } }, "UnityEnvironment.step": { "total": 0.07897069000000556, "count": 1, "is_parallel": true, "self": 0.0006831480000073498, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005036219999965397, "count": 1, "is_parallel": true, "self": 0.0005036219999965397 }, "communicator.exchange": { "total": 0.07441088099994886, "count": 1, "is_parallel": true, "self": 0.07441088099994886 }, "steps_from_proto": { "total": 0.003373039000052813, "count": 1, "is_parallel": true, "self": 0.0013687670007129782, "children": { "_process_rank_one_or_two_observation": { "total": 0.002004271999339835, "count": 10, "is_parallel": true, "self": 0.002004271999339835 } } } } } } }, "UnityEnvironment.step": { "total": 109.80138764601725, "count": 7263, "is_parallel": true, "self": 4.500908722024633, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3794146300078864, "count": 7263, "is_parallel": true, "self": 2.3794146300078864 }, "communicator.exchange": { "total": 86.55531314499422, "count": 7263, "is_parallel": true, "self": 86.55531314499422 }, "steps_from_proto": { "total": 16.365751148990512, "count": 7263, "is_parallel": true, "self": 3.015981797954737, "children": { "_process_rank_one_or_two_observation": { "total": 13.349769351035775, "count": 72630, "is_parallel": true, "self": 13.349769351035775 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001425604000360181, "count": 1, "self": 0.001425604000360181, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 204.96596370299812, "count": 194646, "is_parallel": true, "self": 4.581322357907993, "children": { "process_trajectory": { "total": 112.13210191809003, "count": 194646, "is_parallel": true, "self": 111.92670309709001, "children": { "RLTrainer._checkpoint": { "total": 0.20539882100001705, "count": 1, "is_parallel": true, "self": 0.20539882100001705 } } }, "_update_policy": { "total": 88.2525394270001, "count": 36, "is_parallel": true, "self": 35.320939524002824, "children": { "TorchPPOOptimizer.update": { "total": 52.93159990299728, "count": 1833, "is_parallel": true, "self": 52.93159990299728 } } } } } } } } }, "TrainerController._save_models": { "total": 0.3117702599997756, "count": 1, "self": 0.0019030459998248261, "children": { "RLTrainer._checkpoint": { "total": 0.30986721399995076, "count": 1, "self": 0.30986721399995076 } } } } } } }