{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8195419311523438, "min": 0.8195419311523438, "max": 2.866346836090088, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7824.986328125, "min": 7824.986328125, "max": 29417.318359375, "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": 12.913717269897461, "min": 0.34542855620384216, "max": 12.913717269897461, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2518.1748046875, "min": 67.01313781738281, "max": 2619.739501953125, "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": 0.06470301406514802, "min": 0.0639749136588958, "max": 0.07659316053554101, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25881205626059206, "min": 0.2558996546355832, "max": 0.3827492083221966, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1982655808621762, "min": 0.1153135336627362, "max": 0.27347409070706835, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7930623234487048, "min": 0.4612541346509448, "max": 1.3673704535353417, "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": 25.386363636363637, "min": 3.5454545454545454, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1117.0, "min": 156.0, "max": 1406.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.386363636363637, "min": 3.5454545454545454, "max": 25.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1117.0, "min": 156.0, "max": 1406.0, "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": "1715722932", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715723405" }, "total": 473.729389447, "count": 1, "self": 0.4512150129999668, "children": { "run_training.setup": { "total": 0.05570893500004104, "count": 1, "self": 0.05570893500004104 }, "TrainerController.start_learning": { "total": 473.222465499, "count": 1, "self": 0.5716283749993636, "children": { "TrainerController._reset_env": { "total": 3.118788202000019, "count": 1, "self": 3.118788202000019 }, "TrainerController.advance": { "total": 469.43357349800056, "count": 18199, "self": 0.28557912500247085, "children": { "env_step": { "total": 469.1479943729981, "count": 18199, "self": 308.27130485800984, "children": { "SubprocessEnvManager._take_step": { "total": 160.58177731899212, "count": 18199, "self": 1.5332245089941807, "children": { "TorchPolicy.evaluate": { "total": 159.04855280999794, "count": 18199, "self": 159.04855280999794 } } }, "workers": { "total": 0.29491219599611895, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 472.0623431619997, "count": 18199, "is_parallel": true, "self": 238.87252679501717, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005405574999997498, "count": 1, "is_parallel": true, "self": 0.003702929000041877, "children": { "_process_rank_one_or_two_observation": { "total": 0.001702645999955621, "count": 10, "is_parallel": true, "self": 0.001702645999955621 } } }, "UnityEnvironment.step": { "total": 0.062376567999990584, "count": 1, "is_parallel": true, "self": 0.000716001999933269, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038589900003671573, "count": 1, "is_parallel": true, "self": 0.00038589900003671573 }, "communicator.exchange": { "total": 0.059150853000005554, "count": 1, "is_parallel": true, "self": 0.059150853000005554 }, "steps_from_proto": { "total": 0.002123814000015045, "count": 1, "is_parallel": true, "self": 0.00040047100003448577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017233429999805594, "count": 10, "is_parallel": true, "self": 0.0017233429999805594 } } } } } } }, "UnityEnvironment.step": { "total": 233.18981636698254, "count": 18198, "is_parallel": true, "self": 10.578765525978099, "children": { "UnityEnvironment._generate_step_input": { "total": 5.68559340000013, "count": 18198, "is_parallel": true, "self": 5.68559340000013 }, "communicator.exchange": { "total": 181.21853741400372, "count": 18198, "is_parallel": true, "self": 181.21853741400372 }, "steps_from_proto": { "total": 35.70692002700059, "count": 18198, "is_parallel": true, "self": 6.764739665983768, "children": { "_process_rank_one_or_two_observation": { "total": 28.942180361016824, "count": 181980, "is_parallel": true, "self": 28.942180361016824 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014114400005382777, "count": 1, "self": 0.00014114400005382777, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.6223093560325, "count": 682526, "is_parallel": true, "self": 14.758389986060195, "children": { "process_trajectory": { "total": 256.8097963089721, "count": 682526, "is_parallel": true, "self": 255.859881757972, "children": { "RLTrainer._checkpoint": { "total": 0.9499145510001199, "count": 4, "is_parallel": true, "self": 0.9499145510001199 } } }, "_update_policy": { "total": 192.05412306100015, "count": 90, "is_parallel": true, "self": 63.62099278899933, "children": { "TorchPPOOptimizer.update": { "total": 128.43313027200082, "count": 4587, "is_parallel": true, "self": 128.43313027200082 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09833428000001732, "count": 1, "self": 0.000925455000015063, "children": { "RLTrainer._checkpoint": { "total": 0.09740882500000225, "count": 1, "self": 0.09740882500000225 } } } } } } }