ppo-Huggy / run_logs /timers.json
kunalkumarsahoo's picture
Huggy
674934d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072028398513794,
"min": 1.4072028398513794,
"max": 1.4259952306747437,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71879.921875,
"min": 68717.8125,
"max": 77603.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.26991869918699,
"min": 80.26991869918699,
"max": 399.24,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49366.0,
"min": 48711.0,
"max": 50129.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49507.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49507.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4486677646636963,
"min": 0.05318271741271019,
"max": 2.4857800006866455,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1505.9306640625,
"min": 6.594656944274902,
"max": 1505.9306640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.79220309015212,
"min": 1.8289997505564843,
"max": 4.024197415359642,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2332.204900443554,
"min": 226.79596906900406,
"max": 2332.204900443554,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.79220309015212,
"min": 1.8289997505564843,
"max": 4.024197415359642,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2332.204900443554,
"min": 226.79596906900406,
"max": 2332.204900443554,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01783957081950373,
"min": 0.012591486300031346,
"max": 0.019117169821402057,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0535187124585112,
"min": 0.027179216899094173,
"max": 0.05561859186151802,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05935949997769462,
"min": 0.02126001063734293,
"max": 0.06096753627061844,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17807849993308386,
"min": 0.04252002127468586,
"max": 0.17807849993308386,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5311988229666767e-06,
"min": 3.5311988229666767e-06,
"max": 0.00029536372654542504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.059359646890003e-05,
"min": 1.059359646890003e-05,
"max": 0.0008438661187113,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117703333333335,
"min": 0.10117703333333335,
"max": 0.198454575,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30353110000000005,
"min": 0.20749910000000005,
"max": 0.5812887,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.87339633333335e-05,
"min": 6.87339633333335e-05,
"max": 0.004922883292499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002062018900000005,
"min": 0.0002062018900000005,
"max": 0.014066306129999998,
"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": "1710567908",
"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": "1710570301"
},
"total": 2393.143223545,
"count": 1,
"self": 0.4366537920004703,
"children": {
"run_training.setup": {
"total": 0.05501729100001285,
"count": 1,
"self": 0.05501729100001285
},
"TrainerController.start_learning": {
"total": 2392.651552462,
"count": 1,
"self": 4.151915699084384,
"children": {
"TrainerController._reset_env": {
"total": 3.073581971000067,
"count": 1,
"self": 3.073581971000067
},
"TrainerController.advance": {
"total": 2385.3052172729153,
"count": 232404,
"self": 4.541871223832004,
"children": {
"env_step": {
"total": 1888.7734735010729,
"count": 232404,
"self": 1565.1113237470283,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.94261472394874,
"count": 232404,
"self": 16.509244878980326,
"children": {
"TorchPolicy.evaluate": {
"total": 304.4333698449684,
"count": 222936,
"self": 304.4333698449684
}
}
},
"workers": {
"total": 2.7195350300958125,
"count": 232404,
"self": 0.0,
"children": {
"worker_root": {
"total": 2385.586362000991,
"count": 232404,
"is_parallel": true,
"self": 1121.3351496490118,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007982130000527832,
"count": 1,
"is_parallel": true,
"self": 0.00019381000015528116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000604402999897502,
"count": 2,
"is_parallel": true,
"self": 0.000604402999897502
}
}
},
"UnityEnvironment.step": {
"total": 0.07472736099998656,
"count": 1,
"is_parallel": true,
"self": 0.000458749999779684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002035820000401145,
"count": 1,
"is_parallel": true,
"self": 0.0002035820000401145
},
"communicator.exchange": {
"total": 0.07319075100008376,
"count": 1,
"is_parallel": true,
"self": 0.07319075100008376
},
"steps_from_proto": {
"total": 0.0008742780000829953,
"count": 1,
"is_parallel": true,
"self": 0.0002216170000792772,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006526610000037181,
"count": 2,
"is_parallel": true,
"self": 0.0006526610000037181
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1264.2512123519791,
"count": 232403,
"is_parallel": true,
"self": 38.75229518305332,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.12307072784802,
"count": 232403,
"is_parallel": true,
"self": 82.12307072784802
},
"communicator.exchange": {
"total": 1052.0855504290175,
"count": 232403,
"is_parallel": true,
"self": 1052.0855504290175
},
"steps_from_proto": {
"total": 91.29029601206025,
"count": 232403,
"is_parallel": true,
"self": 32.598705319981946,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.69159069207831,
"count": 464806,
"is_parallel": true,
"self": 58.69159069207831
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.98987254801045,
"count": 232404,
"self": 6.785184184050195,
"children": {
"process_trajectory": {
"total": 148.14865520396052,
"count": 232404,
"self": 146.83807691196057,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3105782919999456,
"count": 10,
"self": 1.3105782919999456
}
}
},
"_update_policy": {
"total": 337.05603315999974,
"count": 97,
"self": 272.9169750150031,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.13905814499662,
"count": 2910,
"self": 64.13905814499662
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.800000952964183e-07,
"count": 1,
"self": 9.800000952964183e-07
},
"TrainerController._save_models": {
"total": 0.12083653899981073,
"count": 1,
"self": 0.002804073999868706,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11803246499994202,
"count": 1,
"self": 0.11803246499994202
}
}
}
}
}
}
}