{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9901952743530273, "min": 0.9901952743530273, "max": 2.858093023300171, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9476.1689453125, "min": 9476.1689453125, "max": 29364.048828125, "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": 13.039182662963867, "min": 0.3300475776195526, "max": 13.039182662963867, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.640625, "min": 64.02922821044922, "max": 2637.1201171875, "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": 0.07041098991883736, "min": 0.06321062187498147, "max": 0.07448228008961807, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28164395967534944, "min": 0.25581604264438035, "max": 0.365421868107446, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18298464677497453, "min": 0.12017580628961178, "max": 0.27638153089027784, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7319385870998981, "min": 0.4807032251584471, "max": 1.381907654451389, "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": 25.977272727272727, "min": 3.272727272727273, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 144.0, "max": 1399.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.272727272727273, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 144.0, "max": 1399.0, "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": "1714275970", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1714276355" }, "total": 385.49424373199963, "count": 1, "self": 0.3221624979992157, "children": { "run_training.setup": { "total": 0.04187027600028159, "count": 1, "self": 0.04187027600028159 }, "TrainerController.start_learning": { "total": 385.13021095800013, "count": 1, "self": 0.455519411007117, "children": { "TrainerController._reset_env": { "total": 2.9715261940000346, "count": 1, "self": 2.9715261940000346 }, "TrainerController.advance": { "total": 381.63563194099333, "count": 18202, "self": 0.21591396896747028, "children": { "env_step": { "total": 381.41971797202586, "count": 18202, "self": 305.9098632990772, "children": { "SubprocessEnvManager._take_step": { "total": 75.30445149798197, "count": 18202, "self": 1.1310707109555551, "children": { "TorchPolicy.evaluate": { "total": 74.17338078702642, "count": 18202, "self": 74.17338078702642 } } }, "workers": { "total": 0.20540317496670468, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 384.4992716609795, "count": 18202, "is_parallel": true, "self": 160.07100608896872, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002414781999959814, "count": 1, "is_parallel": true, "self": 0.0007296179996956198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016851640002641943, "count": 10, "is_parallel": true, "self": 0.0016851640002641943 } } }, "UnityEnvironment.step": { "total": 0.030068005999964953, "count": 1, "is_parallel": true, "self": 0.0005251299999144976, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002776609999273205, "count": 1, "is_parallel": true, "self": 0.0002776609999273205 }, "communicator.exchange": { "total": 0.028138709000359086, "count": 1, "is_parallel": true, "self": 0.028138709000359086 }, "steps_from_proto": { "total": 0.0011265059997640492, "count": 1, "is_parallel": true, "self": 0.00024656000050526927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008799459992587799, "count": 10, "is_parallel": true, "self": 0.0008799459992587799 } } } } } } }, "UnityEnvironment.step": { "total": 224.4282655720108, "count": 18201, "is_parallel": true, "self": 6.062000910098504, "children": { "UnityEnvironment._generate_step_input": { "total": 3.241487348969258, "count": 18201, "is_parallel": true, "self": 3.241487348969258 }, "communicator.exchange": { "total": 196.04301982896504, "count": 18201, "is_parallel": true, "self": 196.04301982896504 }, "steps_from_proto": { "total": 19.08175748397798, "count": 18201, "is_parallel": true, "self": 3.719781940984376, "children": { "_process_rank_one_or_two_observation": { "total": 15.361975542993605, "count": 182010, "is_parallel": true, "self": 15.361975542993605 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017298299962931196, "count": 1, "self": 0.00017298299962931196, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 381.19069378814356, "count": 182510, "is_parallel": true, "self": 2.166003930104125, "children": { "process_trajectory": { "total": 222.46561707003775, "count": 182510, "is_parallel": true, "self": 222.04751378103765, "children": { "RLTrainer._checkpoint": { "total": 0.41810328900010063, "count": 4, "is_parallel": true, "self": 0.41810328900010063 } } }, "_update_policy": { "total": 156.55907278800169, "count": 90, "is_parallel": true, "self": 32.54577030198925, "children": { "TorchPPOOptimizer.update": { "total": 124.01330248601244, "count": 4587, "is_parallel": true, "self": 124.01330248601244 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06736042900001848, "count": 1, "self": 0.001009151000289421, "children": { "RLTrainer._checkpoint": { "total": 0.06635127799972906, "count": 1, "self": 0.06635127799972906 } } } } } } }