{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4055931568145752, "min": 1.4055931568145752, "max": 1.4270373582839966, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70417.40625, "min": 68428.609375, "max": 76492.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.62805872756933, "min": 80.62805872756933, "max": 404.64516129032256, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49425.0, "min": 48957.0, "max": 50176.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49551.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49551.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3590481281280518, "min": 0.06241513416171074, "max": 2.4633281230926514, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1446.0965576171875, "min": 7.677061557769775, "max": 1458.290283203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7226456421234477, "min": 1.7738394325341635, "max": 3.9370116261211603, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2281.9817786216736, "min": 218.18225020170212, "max": 2330.710882663727, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7226456421234477, "min": 1.7738394325341635, "max": 3.9370116261211603, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2281.9817786216736, "min": 218.18225020170212, "max": 2330.710882663727, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01997078958762965, "min": 0.012955856374658955, "max": 0.021696313582166716, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05991236876288895, "min": 0.02591171274931791, "max": 0.06508894074650015, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05910759766896565, "min": 0.022517221265782913, "max": 0.059463305026292795, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17732279300689696, "min": 0.04503444253156583, "max": 0.17732279300689696, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6608487797500017e-06, "min": 3.6608487797500017e-06, "max": 0.0002953629015456999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0982546339250005e-05, "min": 1.0982546339250005e-05, "max": 0.0008443840685386498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122024999999997, "min": 0.10122024999999997, "max": 0.19845430000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036607499999999, "min": 0.20758164999999995, "max": 0.58146135, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.089047500000002e-05, "min": 7.089047500000002e-05, "max": 0.00492286957, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021267142500000006, "min": 0.00021267142500000006, "max": 0.014074921364999998, "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": "1700214275", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700216812" }, "total": 2537.830096983, "count": 1, "self": 0.4367949020006563, "children": { "run_training.setup": { "total": 0.04682539199998814, "count": 1, "self": 0.04682539199998814 }, "TrainerController.start_learning": { "total": 2537.3464766889997, "count": 1, "self": 4.605954492046749, "children": { "TrainerController._reset_env": { "total": 9.236345448000009, "count": 1, "self": 9.236345448000009 }, "TrainerController.advance": { "total": 2523.402872253953, "count": 232439, "self": 4.819294213919875, "children": { "env_step": { "total": 1988.6578934120143, "count": 232439, "self": 1642.366415980062, "children": { "SubprocessEnvManager._take_step": { "total": 343.3100875850108, "count": 232439, "self": 17.277936167001712, "children": { "TorchPolicy.evaluate": { "total": 326.0321514180091, "count": 222922, "self": 326.0321514180091 } } }, "workers": { "total": 2.981389846941653, "count": 232439, "self": 0.0, "children": { "worker_root": { "total": 2529.691901345044, "count": 232439, "is_parallel": true, "self": 1195.696570615062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000796127000000979, "count": 1, "is_parallel": true, "self": 0.0002106880000098954, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005854389999910836, "count": 2, "is_parallel": true, "self": 0.0005854389999910836 } } }, "UnityEnvironment.step": { "total": 0.029904057999999623, "count": 1, "is_parallel": true, "self": 0.0003049349999741935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023310100002049694, "count": 1, "is_parallel": true, "self": 0.00023310100002049694 }, "communicator.exchange": { "total": 0.02862245800000096, "count": 1, "is_parallel": true, "self": 0.02862245800000096 }, "steps_from_proto": { "total": 0.0007435640000039712, "count": 1, "is_parallel": true, "self": 0.0002106849999847782, "children": { "_process_rank_one_or_two_observation": { "total": 0.000532879000019193, "count": 2, "is_parallel": true, "self": 0.000532879000019193 } } } } } } }, "UnityEnvironment.step": { "total": 1333.9953307299818, "count": 232438, "is_parallel": true, "self": 41.501984217005656, "children": { "UnityEnvironment._generate_step_input": { "total": 85.10716638798681, "count": 232438, "is_parallel": true, "self": 85.10716638798681 }, "communicator.exchange": { "total": 1114.801575842021, "count": 232438, "is_parallel": true, "self": 1114.801575842021 }, "steps_from_proto": { "total": 92.58460428296817, "count": 232438, "is_parallel": true, "self": 32.34738853596778, "children": { "_process_rank_one_or_two_observation": { "total": 60.23721574700039, "count": 464876, "is_parallel": true, "self": 60.23721574700039 } } } } } } } } } } }, "trainer_advance": { "total": 529.9256846280184, "count": 232439, "self": 6.95041913105365, "children": { "process_trajectory": { "total": 159.82517880996483, "count": 232439, "self": 158.48446343596538, "children": { "RLTrainer._checkpoint": { "total": 1.3407153739994442, "count": 10, "self": 1.3407153739994442 } } }, "_update_policy": { "total": 363.1500866869999, "count": 97, "self": 298.243498106, "children": { "TorchPPOOptimizer.update": { "total": 64.90658858099988, "count": 2910, "self": 64.90658858099988 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.10130354900002203, "count": 1, "self": 0.0023317260001931572, "children": { "RLTrainer._checkpoint": { "total": 0.09897182299982887, "count": 1, "self": 0.09897182299982887 } } } } } } }