ppo-Huggy / run_logs /timers.json
chaowu's picture
Huggy
7522da8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4109400510787964,
"min": 1.4109400510787964,
"max": 1.4324779510498047,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69958.640625,
"min": 68212.375,
"max": 79499.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.25373134328358,
"min": 79.63225806451612,
"max": 385.4651162790698,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49448.0,
"min": 48857.0,
"max": 50165.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999938.0,
"min": 49796.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999938.0,
"min": 49796.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.426727056503296,
"min": 0.11380404233932495,
"max": 2.485243320465088,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1300.7257080078125,
"min": 15.135937690734863,
"max": 1486.8170166015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.685706184537553,
"min": 1.7305263094884111,
"max": 4.032955277350641,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1975.5385149121284,
"min": 230.1599991619587,
"max": 2375.4106583595276,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.685706184537553,
"min": 1.7305263094884111,
"max": 4.032955277350641,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1975.5385149121284,
"min": 230.1599991619587,
"max": 2375.4106583595276,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016003637643815533,
"min": 0.012526251435944383,
"max": 0.02011203691654373,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0480109129314466,
"min": 0.025052502871888767,
"max": 0.05547105134852851,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054236112038294475,
"min": 0.021039290043214958,
"max": 0.06323312069806787,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16270833611488342,
"min": 0.042078580086429916,
"max": 0.18969936209420363,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6266987911333347e-06,
"min": 3.6266987911333347e-06,
"max": 0.000295330876556375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0880096373400004e-05,
"min": 1.0880096373400004e-05,
"max": 0.0008437896187368,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120886666666666,
"min": 0.10120886666666666,
"max": 0.198443625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362659999999997,
"min": 0.20757115000000004,
"max": 0.5812632,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.03224466666667e-05,
"min": 7.03224466666667e-05,
"max": 0.004922336887500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002109673400000001,
"min": 0.0002109673400000001,
"max": 0.014065033680000004,
"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": "1687460246",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687462662"
},
"total": 2416.061542667,
"count": 1,
"self": 0.7899610399999801,
"children": {
"run_training.setup": {
"total": 0.06207572599998912,
"count": 1,
"self": 0.06207572599998912
},
"TrainerController.start_learning": {
"total": 2415.2095059010003,
"count": 1,
"self": 4.202194405043883,
"children": {
"TrainerController._reset_env": {
"total": 5.081882511000003,
"count": 1,
"self": 5.081882511000003
},
"TrainerController.advance": {
"total": 2405.7369941549564,
"count": 232384,
"self": 4.40432936881507,
"children": {
"env_step": {
"total": 1874.0286762460855,
"count": 232384,
"self": 1575.5149335641513,
"children": {
"SubprocessEnvManager._take_step": {
"total": 295.7127491439662,
"count": 232384,
"self": 17.246391388957818,
"children": {
"TorchPolicy.evaluate": {
"total": 278.4663577550084,
"count": 222984,
"self": 278.4663577550084
}
}
},
"workers": {
"total": 2.8009935379679973,
"count": 232384,
"self": 0.0,
"children": {
"worker_root": {
"total": 2407.2071358249977,
"count": 232384,
"is_parallel": true,
"self": 1120.476309985046,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011343060000399419,
"count": 1,
"is_parallel": true,
"self": 0.00033233400006338343,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008019719999765584,
"count": 2,
"is_parallel": true,
"self": 0.0008019719999765584
}
}
},
"UnityEnvironment.step": {
"total": 0.029238536999969256,
"count": 1,
"is_parallel": true,
"self": 0.0003578719999950408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023856799998611677,
"count": 1,
"is_parallel": true,
"self": 0.00023856799998611677
},
"communicator.exchange": {
"total": 0.02779638200001955,
"count": 1,
"is_parallel": true,
"self": 0.02779638200001955
},
"steps_from_proto": {
"total": 0.0008457149999685498,
"count": 1,
"is_parallel": true,
"self": 0.0002602829999887035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005854319999798463,
"count": 2,
"is_parallel": true,
"self": 0.0005854319999798463
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.7308258399516,
"count": 232383,
"is_parallel": true,
"self": 39.817741563914524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.49151919799124,
"count": 232383,
"is_parallel": true,
"self": 78.49151919799124
},
"communicator.exchange": {
"total": 1072.9937586090298,
"count": 232383,
"is_parallel": true,
"self": 1072.9937586090298
},
"steps_from_proto": {
"total": 95.4278064690161,
"count": 232383,
"is_parallel": true,
"self": 33.45832736594127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.96947910307483,
"count": 464766,
"is_parallel": true,
"self": 61.96947910307483
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.3039885400559,
"count": 232384,
"self": 6.612941875089632,
"children": {
"process_trajectory": {
"total": 137.70183592396734,
"count": 232384,
"self": 136.3210050929681,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3808308309992299,
"count": 10,
"self": 1.3808308309992299
}
}
},
"_update_policy": {
"total": 382.98921074099894,
"count": 97,
"self": 321.74351591500897,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.24569482598997,
"count": 2910,
"self": 61.24569482598997
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5599998732795939e-06,
"count": 1,
"self": 1.5599998732795939e-06
},
"TrainerController._save_models": {
"total": 0.18843327000013232,
"count": 1,
"self": 0.0026811439997800335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1857521260003523,
"count": 1,
"self": 0.1857521260003523
}
}
}
}
}
}
}