{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408309817314148, "min": 1.408309817314148, "max": 1.4313771724700928, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70267.6171875, "min": 68652.0625, "max": 77671.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 170.36986301369862, "min": 108.46916299559471, "max": 403.352, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49748.0, "min": 49228.0, "max": 50419.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49795.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49795.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.137913942337036, "min": 0.1004694402217865, "max": 2.3842742443084717, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 624.2708740234375, "min": 12.458210945129395, "max": 1055.901123046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.147535459227758, "min": 1.9728028660099353, "max": 3.7365421282543854, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 919.0803540945053, "min": 244.62755538523197, "max": 1633.7183106541634, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.147535459227758, "min": 1.9728028660099353, "max": 3.7365421282543854, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 919.0803540945053, "min": 244.62755538523197, "max": 1633.7183106541634, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018059810208311926, "min": 0.01385816164353552, "max": 0.020582606475606252, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03611962041662385, "min": 0.02771632328707104, "max": 0.05947090209810995, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.03168686029190818, "min": 0.022551580456395943, "max": 0.06686549426780806, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.06337372058381636, "min": 0.04510316091279189, "max": 0.20059648280342418, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.425323524925012e-06, "min": 4.425323524925012e-06, "max": 0.0002953529265490249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.850647049850023e-06, "min": 8.850647049850023e-06, "max": 0.0008441713686095499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101475075, "min": 0.101475075, "max": 0.19845097500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20295015, "min": 0.20295015, "max": 0.5813904500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.360624250000015e-05, "min": 8.360624250000015e-05, "max": 0.0049227036525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001672124850000003, "min": 0.0001672124850000003, "max": 0.014071383454999996, "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": "1673874777", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673876994" }, "total": 2217.3013282869997, "count": 1, "self": 0.39013234300000477, "children": { "run_training.setup": { "total": 0.10862126400002126, "count": 1, "self": 0.10862126400002126 }, "TrainerController.start_learning": { "total": 2216.80257468, "count": 1, "self": 3.7674800630406935, "children": { "TrainerController._reset_env": { "total": 9.998401427999966, "count": 1, "self": 9.998401427999966 }, "TrainerController.advance": { "total": 2202.9094371459596, "count": 230064, "self": 4.2288819780237645, "children": { "env_step": { "total": 1743.96761652006, "count": 230064, "self": 1463.6521337211188, "children": { "SubprocessEnvManager._take_step": { "total": 277.68738174493046, "count": 230064, "self": 14.190580692939193, "children": { "TorchPolicy.evaluate": { "total": 263.49680105199127, "count": 223062, "self": 65.50508261197547, "children": { "TorchPolicy.sample_actions": { "total": 197.9917184400158, "count": 223062, "self": 197.9917184400158 } } } } }, "workers": { "total": 2.6281010540104717, "count": 230064, "self": 0.0, "children": { "worker_root": { "total": 2209.1100403460405, "count": 230064, "is_parallel": true, "self": 1002.7862379129513, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019824009999638292, "count": 1, "is_parallel": true, "self": 0.0003523809999705918, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016300199999932374, "count": 2, "is_parallel": true, "self": 0.0016300199999932374 } } }, "UnityEnvironment.step": { "total": 0.04831391599998369, "count": 1, "is_parallel": true, "self": 0.0002906369999209346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002033690000189381, "count": 1, "is_parallel": true, "self": 0.0002033690000189381 }, "communicator.exchange": { "total": 0.04692314900000838, "count": 1, "is_parallel": true, "self": 0.04692314900000838 }, "steps_from_proto": { "total": 0.0008967610000354398, "count": 1, "is_parallel": true, "self": 0.00024204600003940868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006547149999960311, "count": 2, "is_parallel": true, "self": 0.0006547149999960311 } } } } } } }, "UnityEnvironment.step": { "total": 1206.3238024330892, "count": 230063, "is_parallel": true, "self": 34.657858344101214, "children": { "UnityEnvironment._generate_step_input": { "total": 76.50286119799478, "count": 230063, "is_parallel": true, "self": 76.50286119799478 }, "communicator.exchange": { "total": 1002.0049849219098, "count": 230063, "is_parallel": true, "self": 1002.0049849219098 }, "steps_from_proto": { "total": 93.15809796908343, "count": 230063, "is_parallel": true, "self": 38.24168791200361, "children": { "_process_rank_one_or_two_observation": { "total": 54.916410057079815, "count": 460126, "is_parallel": true, "self": 54.916410057079815 } } } } } } } } } } }, "trainer_advance": { "total": 454.71293864787606, "count": 230064, "self": 6.1714097657586535, "children": { "process_trajectory": { "total": 140.49812303811757, "count": 230064, "self": 139.30520981411792, "children": { "RLTrainer._checkpoint": { "total": 1.1929132239996534, "count": 10, "self": 1.1929132239996534 } } }, "_update_policy": { "total": 308.04340584399984, "count": 96, "self": 254.34924633000355, "children": { "TorchPPOOptimizer.update": { "total": 53.69415951399628, "count": 2880, "self": 53.69415951399628 } } } } } } }, "trainer_threads": { "total": 9.559998943586834e-07, "count": 1, "self": 9.559998943586834e-07 }, "TrainerController._save_models": { "total": 0.12725508699986676, "count": 1, "self": 0.0019962429996667197, "children": { "RLTrainer._checkpoint": { "total": 0.12525884400020004, "count": 1, "self": 0.12525884400020004 } } } } } } }