{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4201579093933105, "min": 1.419278860092163, "max": 1.4321491718292236, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71225.1796875, "min": 69498.9296875, "max": 77390.4375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.57307060755336, "min": 77.95918367346938, "max": 413.7107438016529, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49069.0, "min": 49069.0, "max": 50059.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999939.0, "min": 49824.0, "max": 1999939.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999939.0, "min": 49824.0, "max": 1999939.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.521683931350708, "min": 0.11130113899707794, "max": 2.521683931350708, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1535.70556640625, "min": 13.356136322021484, "max": 1588.395263671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.889546479987002, "min": 1.7708680627246698, "max": 3.9346768613964995, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2368.733806312084, "min": 212.50416752696037, "max": 2466.416868507862, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.889546479987002, "min": 1.7708680627246698, "max": 3.9346768613964995, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2368.733806312084, "min": 212.50416752696037, "max": 2466.416868507862, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.012846435138878102, "min": 0.010219733428231039, "max": 0.01698827888079298, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.038539305416634306, "min": 0.020439466856462078, "max": 0.05096483664237894, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06719972593364892, "min": 0.023840155866410997, "max": 0.0694670904693859, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.20159917780094677, "min": 0.047680311732821994, "max": 0.20159917780094677, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.314248895283338e-06, "min": 3.314248895283338e-06, "max": 0.0002953539015487, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.942746685850014e-06, "min": 9.942746685850014e-06, "max": 0.0008439622686792499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110471666666666, "min": 0.10110471666666666, "max": 0.19845130000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30331415, "min": 0.20737780000000003, "max": 0.5813207499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.512536166666676e-05, "min": 6.512536166666676e-05, "max": 0.00492271987, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019537608500000026, "min": 0.00019537608500000026, "max": 0.014067905424999999, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702822383", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702824980" }, "total": 2596.912186175, "count": 1, "self": 0.44447117500021704, "children": { "run_training.setup": { "total": 0.04965602900006161, "count": 1, "self": 0.04965602900006161 }, "TrainerController.start_learning": { "total": 2596.418058971, "count": 1, "self": 5.001683822909399, "children": { "TrainerController._reset_env": { "total": 3.602352249999967, "count": 1, "self": 3.602352249999967 }, "TrainerController.advance": { "total": 2587.691879378091, "count": 232630, "self": 5.3793879923264285, "children": { "env_step": { "total": 2083.4217654838494, "count": 232630, "self": 1726.1077629278277, "children": { "SubprocessEnvManager._take_step": { "total": 354.022131224996, "count": 232630, "self": 19.116693158031694, "children": { "TorchPolicy.evaluate": { "total": 334.9054380669643, "count": 222901, "self": 334.9054380669643 } } }, "workers": { "total": 3.2918713310257317, "count": 232630, "self": 0.0, "children": { "worker_root": { "total": 2588.3533399469657, "count": 232630, "is_parallel": true, "self": 1194.3192466388807, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007720969999809313, "count": 1, "is_parallel": true, "self": 0.0002573690001099749, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005147279998709564, "count": 2, "is_parallel": true, "self": 0.0005147279998709564 } } }, "UnityEnvironment.step": { "total": 0.05292834200008656, "count": 1, "is_parallel": true, "self": 0.0003793430000769149, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023731300007057143, "count": 1, "is_parallel": true, "self": 0.00023731300007057143 }, "communicator.exchange": { "total": 0.05158090299983087, "count": 1, "is_parallel": true, "self": 0.05158090299983087 }, "steps_from_proto": { "total": 0.0007307830001082039, "count": 1, "is_parallel": true, "self": 0.0001967250000234344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005340580000847694, "count": 2, "is_parallel": true, "self": 0.0005340580000847694 } } } } } } }, "UnityEnvironment.step": { "total": 1394.034093308085, "count": 232629, "is_parallel": true, "self": 43.6209058761026, "children": { "UnityEnvironment._generate_step_input": { "total": 92.50425876803115, "count": 232629, "is_parallel": true, "self": 92.50425876803115 }, "communicator.exchange": { "total": 1158.5261436269318, "count": 232629, "is_parallel": true, "self": 1158.5261436269318 }, "steps_from_proto": { "total": 99.3827850370194, "count": 232629, "is_parallel": true, "self": 36.789431042913975, "children": { "_process_rank_one_or_two_observation": { "total": 62.59335399410543, "count": 465258, "is_parallel": true, "self": 62.59335399410543 } } } } } } } } } } }, "trainer_advance": { "total": 498.8907259019154, "count": 232630, "self": 7.949505843908582, "children": { "process_trajectory": { "total": 169.10769885100763, "count": 232630, "self": 167.8436927170069, "children": { "RLTrainer._checkpoint": { "total": 1.2640061340007378, "count": 10, "self": 1.2640061340007378 } } }, "_update_policy": { "total": 321.8335212069992, "count": 97, "self": 269.42338412099866, "children": { "TorchPPOOptimizer.update": { "total": 52.41013708600053, "count": 1755, "self": 52.41013708600053 } } } } } } }, "trainer_threads": { "total": 1.3499998203769792e-06, "count": 1, "self": 1.3499998203769792e-06 }, "TrainerController._save_models": { "total": 0.1221421699997336, "count": 1, "self": 0.002071845000045869, "children": { "RLTrainer._checkpoint": { "total": 0.12007032499968773, "count": 1, "self": 0.12007032499968773 } } } } } } }