{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0581101179122925, "min": 1.0581101179122925, "max": 2.8736603260040283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10126.1142578125, "min": 10126.1142578125, "max": 29460.765625, "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": 12.786876678466797, "min": 0.42007485032081604, "max": 12.786876678466797, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.44091796875, "min": 81.49452209472656, "max": 2602.491455078125, "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": 0.06922008410733457, "min": 0.06343485222713949, "max": 0.07553110151233804, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2768803364293383, "min": 0.2584552082877838, "max": 0.3776555075616902, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2027629515630942, "min": 0.12016408217217153, "max": 0.28644669424085056, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8110518062523768, "min": 0.48065632868868613, "max": 1.4322334712042528, "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": 24.954545454545453, "min": 3.25, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 143.0, "max": 1388.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.25, "max": 25.318181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 143.0, "max": 1388.0, "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": "1690176134", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690176517" }, "total": 382.38411989500014, "count": 1, "self": 0.2748969490003219, "children": { "run_training.setup": { "total": 0.03201711599990631, "count": 1, "self": 0.03201711599990631 }, "TrainerController.start_learning": { "total": 382.0772058299999, "count": 1, "self": 0.5058210050299294, "children": { "TrainerController._reset_env": { "total": 4.112014843999987, "count": 1, "self": 4.112014843999987 }, "TrainerController.advance": { "total": 377.3209073719697, "count": 18204, "self": 0.23884082497397685, "children": { "env_step": { "total": 377.08206654699575, "count": 18204, "self": 270.3380936220026, "children": { "SubprocessEnvManager._take_step": { "total": 106.49914258599347, "count": 18204, "self": 1.4339597059824882, "children": { "TorchPolicy.evaluate": { "total": 105.06518288001098, "count": 18204, "self": 105.06518288001098 } } }, "workers": { "total": 0.24483033899969087, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 381.2773753730155, "count": 18204, "is_parallel": true, "self": 192.256163041033, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056694060001518665, "count": 1, "is_parallel": true, "self": 0.004190550999965126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014788550001867407, "count": 10, "is_parallel": true, "self": 0.0014788550001867407 } } }, "UnityEnvironment.step": { "total": 0.033565814999974464, "count": 1, "is_parallel": true, "self": 0.000665642000058142, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00034331799997744383, "count": 1, "is_parallel": true, "self": 0.00034331799997744383 }, "communicator.exchange": { "total": 0.030466515999933108, "count": 1, "is_parallel": true, "self": 0.030466515999933108 }, "steps_from_proto": { "total": 0.0020903390000057698, "count": 1, "is_parallel": true, "self": 0.0003696509995734232, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017206880004323466, "count": 10, "is_parallel": true, "self": 0.0017206880004323466 } } } } } } }, "UnityEnvironment.step": { "total": 189.0212123319825, "count": 18203, "is_parallel": true, "self": 9.154373794015783, "children": { "UnityEnvironment._generate_step_input": { "total": 4.619414255005495, "count": 18203, "is_parallel": true, "self": 4.619414255005495 }, "communicator.exchange": { "total": 146.4987920099834, "count": 18203, "is_parallel": true, "self": 146.4987920099834 }, "steps_from_proto": { "total": 28.74863227297783, "count": 18203, "is_parallel": true, "self": 5.20255184003031, "children": { "_process_rank_one_or_two_observation": { "total": 23.54608043294752, "count": 182030, "is_parallel": true, "self": 23.54608043294752 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015343300015047134, "count": 1, "self": 0.00015343300015047134, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 376.0291802790109, "count": 218975, "is_parallel": true, "self": 4.337060073941075, "children": { "process_trajectory": { "total": 206.82462146206944, "count": 218975, "is_parallel": true, "self": 206.0464459250693, "children": { "RLTrainer._checkpoint": { "total": 0.778175537000152, "count": 4, "is_parallel": true, "self": 0.778175537000152 } } }, "_update_policy": { "total": 164.8674987430004, "count": 90, "is_parallel": true, "self": 45.155555061008954, "children": { "TorchPPOOptimizer.update": { "total": 119.71194368199144, "count": 4587, "is_parallel": true, "self": 119.71194368199144 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13830917600012071, "count": 1, "self": 0.0008863590001055854, "children": { "RLTrainer._checkpoint": { "total": 0.13742281700001513, "count": 1, "self": 0.13742281700001513 } } } } } } }