{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1024081707000732, "min": 1.10026216506958, "max": 2.856454849243164, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10550.0458984375, "min": 10550.0458984375, "max": 29315.794921875, "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": 12.009637832641602, "min": 0.3364394009113312, "max": 12.009637832641602, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2341.87939453125, "min": 65.26924133300781, "max": 2405.82568359375, "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": 0.06478022901604823, "min": 0.06165591435054404, "max": 0.0717566156207456, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2591209160641929, "min": 0.2591209160641929, "max": 0.358783078103728, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20832681349095175, "min": 0.11242951576566032, "max": 0.2632914166532311, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.833307253963807, "min": 0.4497180630626413, "max": 1.2701855842389314, "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": 23.318181818181817, "min": 3.25, "max": 23.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1026.0, "min": 143.0, "max": 1295.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.318181818181817, "min": 3.25, "max": 23.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1026.0, "min": 143.0, "max": 1295.0, "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": "1692560490", "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": "1692560979" }, "total": 488.55923680500007, "count": 1, "self": 0.4374861720000922, "children": { "run_training.setup": { "total": 0.063408126000013, "count": 1, "self": 0.063408126000013 }, "TrainerController.start_learning": { "total": 488.05834250699996, "count": 1, "self": 0.5529387350081834, "children": { "TrainerController._reset_env": { "total": 5.1489451169999825, "count": 1, "self": 5.1489451169999825 }, "TrainerController.advance": { "total": 482.2022671659919, "count": 18203, "self": 0.2927138469933652, "children": { "env_step": { "total": 481.9095533189985, "count": 18203, "self": 351.5208225259958, "children": { "SubprocessEnvManager._take_step": { "total": 130.08755755799712, "count": 18203, "self": 1.7968106339897076, "children": { "TorchPolicy.evaluate": { "total": 128.2907469240074, "count": 18203, "self": 128.2907469240074 } } }, "workers": { "total": 0.30117323500559223, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 486.5233169610107, "count": 18203, "is_parallel": true, "self": 229.8028155800032, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00657825899997988, "count": 1, "is_parallel": true, "self": 0.004116755000154626, "children": { "_process_rank_one_or_two_observation": { "total": 0.002461503999825254, "count": 10, "is_parallel": true, "self": 0.002461503999825254 } } }, "UnityEnvironment.step": { "total": 0.05126075799995533, "count": 1, "is_parallel": true, "self": 0.0004934239998988232, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042092700005014194, "count": 1, "is_parallel": true, "self": 0.00042092700005014194 }, "communicator.exchange": { "total": 0.04812258300000849, "count": 1, "is_parallel": true, "self": 0.04812258300000849 }, "steps_from_proto": { "total": 0.002223823999997876, "count": 1, "is_parallel": true, "self": 0.00046531600003163476, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017585079999662412, "count": 10, "is_parallel": true, "self": 0.0017585079999662412 } } } } } } }, "UnityEnvironment.step": { "total": 256.7205013810075, "count": 18202, "is_parallel": true, "self": 10.812545722006973, "children": { "UnityEnvironment._generate_step_input": { "total": 5.571292762997018, "count": 18202, "is_parallel": true, "self": 5.571292762997018 }, "communicator.exchange": { "total": 202.19117444200077, "count": 18202, "is_parallel": true, "self": 202.19117444200077 }, "steps_from_proto": { "total": 38.14548845400276, "count": 18202, "is_parallel": true, "self": 6.918880500996181, "children": { "_process_rank_one_or_two_observation": { "total": 31.226607953006578, "count": 182020, "is_parallel": true, "self": 31.226607953006578 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001359919999686099, "count": 1, "self": 0.0001359919999686099, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 478.2421423839958, "count": 444096, "is_parallel": true, "self": 10.538501273018767, "children": { "process_trajectory": { "total": 263.92305058797774, "count": 444096, "is_parallel": true, "self": 262.0872182079777, "children": { "RLTrainer._checkpoint": { "total": 1.8358323800000562, "count": 4, "is_parallel": true, "self": 1.8358323800000562 } } }, "_update_policy": { "total": 203.78059052299932, "count": 90, "is_parallel": true, "self": 81.91868447400088, "children": { "TorchPPOOptimizer.update": { "total": 121.86190604899843, "count": 4587, "is_parallel": true, "self": 121.86190604899843 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1540554969999448, "count": 1, "self": 0.0008774479999829055, "children": { "RLTrainer._checkpoint": { "total": 0.1531780489999619, "count": 1, "self": 0.1531780489999619 } } } } } } }