ppo-Huggy / run_logs /timers.json
DeMuenu's picture
Huggy
b62d44a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3973147869110107,
"min": 1.3973147869110107,
"max": 1.425166368484497,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69868.53125,
"min": 68997.8515625,
"max": 77361.6640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.92071197411003,
"min": 73.83982035928143,
"max": 431.1034482758621,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50009.0,
"min": 48739.0,
"max": 50056.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49789.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49789.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4760520458221436,
"min": -0.02600046433508396,
"max": 2.537992238998413,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1532.67626953125,
"min": -2.990053415298462,
"max": 1658.6285400390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.903020972100136,
"min": 1.7023726147154103,
"max": 4.01877050655555,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2415.9699817299843,
"min": 195.7728506922722,
"max": 2535.487456679344,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.903020972100136,
"min": 1.7023726147154103,
"max": 4.01877050655555,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2415.9699817299843,
"min": 195.7728506922722,
"max": 2535.487456679344,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019688018093115208,
"min": 0.013285127851365056,
"max": 0.020766495262796527,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05906405427934563,
"min": 0.02657025570273011,
"max": 0.06229948578838958,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06599613163206312,
"min": 0.020650579563031592,
"max": 0.07045642801870902,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19798839489618936,
"min": 0.041301159126063185,
"max": 0.20564266592264177,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.505748831450005e-06,
"min": 3.505748831450005e-06,
"max": 0.0002952555015815,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0517246494350015e-05,
"min": 1.0517246494350015e-05,
"max": 0.0008438337187220998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116855000000001,
"min": 0.10116855000000001,
"max": 0.19841850000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30350565,
"min": 0.20752100000000007,
"max": 0.5812778999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.83106450000001e-05,
"min": 6.83106450000001e-05,
"max": 0.004921083149999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020493193500000027,
"min": 0.00020493193500000027,
"max": 0.01406576721,
"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": "1714562356",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714565165"
},
"total": 2808.2073103740004,
"count": 1,
"self": 0.7029299930004527,
"children": {
"run_training.setup": {
"total": 0.06726333300002807,
"count": 1,
"self": 0.06726333300002807
},
"TrainerController.start_learning": {
"total": 2807.437117048,
"count": 1,
"self": 6.132593816877943,
"children": {
"TrainerController._reset_env": {
"total": 3.177432983000017,
"count": 1,
"self": 3.177432983000017
},
"TrainerController.advance": {
"total": 2797.932987260122,
"count": 232958,
"self": 5.608772610125925,
"children": {
"env_step": {
"total": 2267.3493237940634,
"count": 232958,
"self": 1866.4974455811289,
"children": {
"SubprocessEnvManager._take_step": {
"total": 397.1096552500144,
"count": 232958,
"self": 21.13427232993388,
"children": {
"TorchPolicy.evaluate": {
"total": 375.9753829200805,
"count": 222932,
"self": 375.9753829200805
}
}
},
"workers": {
"total": 3.7422229629202093,
"count": 232958,
"self": 0.0,
"children": {
"worker_root": {
"total": 2798.1671865349986,
"count": 232958,
"is_parallel": true,
"self": 1303.3271003070777,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010048910000932665,
"count": 1,
"is_parallel": true,
"self": 0.0002485820001538741,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007563089999393924,
"count": 2,
"is_parallel": true,
"self": 0.0007563089999393924
}
}
},
"UnityEnvironment.step": {
"total": 0.03454892000002019,
"count": 1,
"is_parallel": true,
"self": 0.0004622019999942495,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002502050000430245,
"count": 1,
"is_parallel": true,
"self": 0.0002502050000430245
},
"communicator.exchange": {
"total": 0.033019128999967506,
"count": 1,
"is_parallel": true,
"self": 0.033019128999967506
},
"steps_from_proto": {
"total": 0.0008173840000154087,
"count": 1,
"is_parallel": true,
"self": 0.00021120600001722778,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006061779999981809,
"count": 2,
"is_parallel": true,
"self": 0.0006061779999981809
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1494.840086227921,
"count": 232957,
"is_parallel": true,
"self": 46.5981104870184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.77660869401382,
"count": 232957,
"is_parallel": true,
"self": 89.77660869401382
},
"communicator.exchange": {
"total": 1249.4540321959441,
"count": 232957,
"is_parallel": true,
"self": 1249.4540321959441
},
"steps_from_proto": {
"total": 109.01133485094454,
"count": 232957,
"is_parallel": true,
"self": 37.38149364288506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.62984120805947,
"count": 465914,
"is_parallel": true,
"self": 71.62984120805947
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 524.9748908559326,
"count": 232958,
"self": 8.540132745850542,
"children": {
"process_trajectory": {
"total": 173.56395724708352,
"count": 232958,
"self": 172.01620249308337,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5477547540001524,
"count": 10,
"self": 1.5477547540001524
}
}
},
"_update_policy": {
"total": 342.8708008629985,
"count": 97,
"self": 274.041670637019,
"children": {
"TorchPPOOptimizer.update": {
"total": 68.8291302259795,
"count": 2910,
"self": 68.8291302259795
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1629999789875e-06,
"count": 1,
"self": 1.1629999789875e-06
},
"TrainerController._save_models": {
"total": 0.19410182499996154,
"count": 1,
"self": 0.003861938000227383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19023988699973415,
"count": 1,
"self": 0.19023988699973415
}
}
}
}
}
}
}