{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4103553295135498, "min": 1.4103553295135498, "max": 1.4307044744491577, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71551.5546875, "min": 68914.9765625, "max": 76720.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.03915171288745, "min": 80.03915171288745, "max": 394.1796875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49064.0, "min": 48732.0, "max": 50455.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999959.0, "min": 49833.0, "max": 1999959.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999959.0, "min": 49833.0, "max": 1999959.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3669557571411133, "min": 0.07148709148168564, "max": 2.45257306098938, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1450.94384765625, "min": 9.07886028289795, "max": 1450.94384765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7324916551202585, "min": 1.8688447703057387, "max": 3.9211143009312504, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2288.0173845887184, "min": 237.3432858288288, "max": 2329.2251156568527, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7324916551202585, "min": 1.8688447703057387, "max": 3.9211143009312504, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2288.0173845887184, "min": 237.3432858288288, "max": 2329.2251156568527, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01581921420131241, "min": 0.013663633663478928, "max": 0.020317267078078453, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04745764260393723, "min": 0.027327267326957855, "max": 0.06095180123423536, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05856604927943813, "min": 0.022705509761969247, "max": 0.058660971373319624, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1756981478383144, "min": 0.045411019523938494, "max": 0.1756981478383144, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4648988450666666e-06, "min": 3.4648988450666666e-06, "max": 0.000295340926553025, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.03946965352e-05, "min": 1.03946965352e-05, "max": 0.0008441821686059498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115493333333332, "min": 0.10115493333333332, "max": 0.19844697500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034648, "min": 0.20752410000000004, "max": 0.5813940500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.763117333333337e-05, "min": 6.763117333333337e-05, "max": 0.0049225040525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002028935200000001, "min": 0.0002028935200000001, "max": 0.014071563095, "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": "1738836605", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738839178" }, "total": 2572.792477518, "count": 1, "self": 0.7140247480001563, "children": { "run_training.setup": { "total": 0.029561457999989216, "count": 1, "self": 0.029561457999989216 }, "TrainerController.start_learning": { "total": 2572.048891312, "count": 1, "self": 4.9530883810220985, "children": { "TrainerController._reset_env": { "total": 3.457421586999999, "count": 1, "self": 3.457421586999999 }, "TrainerController.advance": { "total": 2563.515917371977, "count": 232256, "self": 5.155721411122613, "children": { "env_step": { "total": 2053.657457900894, "count": 232256, "self": 1598.5666400489008, "children": { "SubprocessEnvManager._take_step": { "total": 452.0897382831288, "count": 232256, "self": 16.819995366111527, "children": { "TorchPolicy.evaluate": { "total": 435.26974291701725, "count": 222925, "self": 435.26974291701725 } } }, "workers": { "total": 3.001079568864327, "count": 232256, "self": 0.0, "children": { "worker_root": { "total": 2563.917839295976, "count": 232256, "is_parallel": true, "self": 1269.3449312149862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012528180000117572, "count": 1, "is_parallel": true, "self": 0.0004663440000172159, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007864739999945414, "count": 2, "is_parallel": true, "self": 0.0007864739999945414 } } }, "UnityEnvironment.step": { "total": 0.02932002900001862, "count": 1, "is_parallel": true, "self": 0.00033927900000207956, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020603899997695407, "count": 1, "is_parallel": true, "self": 0.00020603899997695407 }, "communicator.exchange": { "total": 0.02807018000004291, "count": 1, "is_parallel": true, "self": 0.02807018000004291 }, "steps_from_proto": { "total": 0.0007045309999966776, "count": 1, "is_parallel": true, "self": 0.00018433899998626657, "children": { "_process_rank_one_or_two_observation": { "total": 0.000520192000010411, "count": 2, "is_parallel": true, "self": 0.000520192000010411 } } } } } } }, "UnityEnvironment.step": { "total": 1294.57290808099, "count": 232255, "is_parallel": true, "self": 39.2913329888363, "children": { "UnityEnvironment._generate_step_input": { "total": 80.88413869510526, "count": 232255, "is_parallel": true, "self": 80.88413869510526 }, "communicator.exchange": { "total": 1083.6846541079894, "count": 232255, "is_parallel": true, "self": 1083.6846541079894 }, "steps_from_proto": { "total": 90.71278228905885, "count": 232255, "is_parallel": true, "self": 30.899166009044393, "children": { "_process_rank_one_or_two_observation": { "total": 59.81361628001446, "count": 464510, "is_parallel": true, "self": 59.81361628001446 } } } } } } } } } } }, "trainer_advance": { "total": 504.70273805996067, "count": 232256, "self": 7.9300669008778755, "children": { "process_trajectory": { "total": 170.85939062408335, "count": 232256, "self": 169.4837144040834, "children": { "RLTrainer._checkpoint": { "total": 1.3756762199999457, "count": 10, "self": 1.3756762199999457 } } }, "_update_policy": { "total": 325.91328053499944, "count": 97, "self": 257.15310815198734, "children": { "TorchPPOOptimizer.update": { "total": 68.7601723830121, "count": 2910, "self": 68.7601723830121 } } } } } } }, "trainer_threads": { "total": 9.300001693191007e-07, "count": 1, "self": 9.300001693191007e-07 }, "TrainerController._save_models": { "total": 0.12246304200016311, "count": 1, "self": 0.0021250680001685396, "children": { "RLTrainer._checkpoint": { "total": 0.12033797399999457, "count": 1, "self": 0.12033797399999457 } } } } } } }