{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40426766872406, "min": 1.404264211654663, "max": 1.4295552968978882, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70518.109375, "min": 68419.453125, "max": 76005.4375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 119.20631067961165, "min": 104.77167019027485, "max": 390.4921875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49113.0, "min": 48923.0, "max": 50167.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999941.0, "min": 49750.0, "max": 1999941.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999941.0, "min": 49750.0, "max": 1999941.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.248845338821411, "min": 0.13949358463287354, "max": 2.399559259414673, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 926.5242919921875, "min": 17.71568489074707, "max": 1087.365234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.3386213362795636, "min": 1.912444867487029, "max": 3.7721763971375255, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1375.5119905471802, "min": 242.88049817085266, "max": 1692.0471985340118, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.3386213362795636, "min": 1.912444867487029, "max": 3.7721763971375255, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1375.5119905471802, "min": 242.88049817085266, "max": 1692.0471985340118, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015218639011921671, "min": 0.014059866468111675, "max": 0.020733682197169402, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.030437278023843342, "min": 0.02811973293622335, "max": 0.05421736154045599, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.043416057868550226, "min": 0.020960330000768107, "max": 0.05247954198469718, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08683211573710045, "min": 0.041920660001536214, "max": 0.15681617272396883, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.4981485006499965e-06, "min": 4.4981485006499965e-06, "max": 0.0002953462515512499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.996297001299993e-06, "min": 8.996297001299993e-06, "max": 0.0008440686186437997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10149935000000002, "min": 0.10149935000000002, "max": 0.19844874999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20299870000000003, "min": 0.20299870000000003, "max": 0.5813562, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.481756499999996e-05, "min": 8.481756499999996e-05, "max": 0.004922592625, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016963512999999993, "min": 0.00016963512999999993, "max": 0.014069674379999996, "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": "1702189591", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702192191" }, "total": 2599.5735341110003, "count": 1, "self": 0.6654527460000281, "children": { "run_training.setup": { "total": 0.05625403700003062, "count": 1, "self": 0.05625403700003062 }, "TrainerController.start_learning": { "total": 2598.851827328, "count": 1, "self": 4.908222920005301, "children": { "TrainerController._reset_env": { "total": 3.429323758999999, "count": 1, "self": 3.429323758999999 }, "TrainerController.advance": { "total": 2590.3555548469944, "count": 230727, "self": 5.182716217044799, "children": { "env_step": { "total": 2067.0577727499663, "count": 230727, "self": 1707.529116964086, "children": { "SubprocessEnvManager._take_step": { "total": 356.3920962160011, "count": 230727, "self": 17.775623409092304, "children": { "TorchPolicy.evaluate": { "total": 338.6164728069088, "count": 223088, "self": 338.6164728069088 } } }, "workers": { "total": 3.1365595698791253, "count": 230727, "self": 0.0, "children": { "worker_root": { "total": 2590.924243266857, "count": 230727, "is_parallel": true, "self": 1213.4123471098872, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008394140000405059, "count": 1, "is_parallel": true, "self": 0.00024111000004722882, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005983039999932771, "count": 2, "is_parallel": true, "self": 0.0005983039999932771 } } }, "UnityEnvironment.step": { "total": 0.03100887599998714, "count": 1, "is_parallel": true, "self": 0.00031571099998473073, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022295499996971557, "count": 1, "is_parallel": true, "self": 0.00022295499996971557 }, "communicator.exchange": { "total": 0.029750298999999814, "count": 1, "is_parallel": true, "self": 0.029750298999999814 }, "steps_from_proto": { "total": 0.0007199110000328801, "count": 1, "is_parallel": true, "self": 0.0002115240000648555, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005083869999680246, "count": 2, "is_parallel": true, "self": 0.0005083869999680246 } } } } } } }, "UnityEnvironment.step": { "total": 1377.51189615697, "count": 230726, "is_parallel": true, "self": 42.12311324513075, "children": { "UnityEnvironment._generate_step_input": { "total": 91.9558201120002, "count": 230726, "is_parallel": true, "self": 91.9558201120002 }, "communicator.exchange": { "total": 1147.6951323329138, "count": 230726, "is_parallel": true, "self": 1147.6951323329138 }, "steps_from_proto": { "total": 95.73783046692523, "count": 230726, "is_parallel": true, "self": 35.45599138203795, "children": { "_process_rank_one_or_two_observation": { "total": 60.28183908488728, "count": 461452, "is_parallel": true, "self": 60.28183908488728 } } } } } } } } } } }, "trainer_advance": { "total": 518.1150658799834, "count": 230727, "self": 7.381976548887053, "children": { "process_trajectory": { "total": 160.10117209709693, "count": 230727, "self": 158.7958695390975, "children": { "RLTrainer._checkpoint": { "total": 1.3053025579994255, "count": 10, "self": 1.3053025579994255 } } }, "_update_policy": { "total": 350.6319172339994, "count": 96, "self": 285.52976012200514, "children": { "TorchPPOOptimizer.update": { "total": 65.10215711199425, "count": 2880, "self": 65.10215711199425 } } } } } } }, "trainer_threads": { "total": 1.4020001799508464e-06, "count": 1, "self": 1.4020001799508464e-06 }, "TrainerController._save_models": { "total": 0.15872440000021015, "count": 1, "self": 0.0022565190001841984, "children": { "RLTrainer._checkpoint": { "total": 0.15646788100002595, "count": 1, "self": 0.15646788100002595 } } } } } } }