ppo-Huggy2 / run_logs /timers.json
Agneev's picture
Huggy2
dd283e1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4034066200256348,
"min": 1.4034066200256348,
"max": 1.4272021055221558,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68859.546875,
"min": 67196.8359375,
"max": 78179.375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.20388349514563,
"min": 84.12564543889845,
"max": 375.3955223880597,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50060.0,
"min": 48854.0,
"max": 50303.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999849.0,
"min": 49998.0,
"max": 1999849.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999849.0,
"min": 49998.0,
"max": 1999849.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.411956548690796,
"min": 0.05230814218521118,
"max": 2.4623374938964844,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1242.1575927734375,
"min": 6.9569830894470215,
"max": 1388.1082763671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7432043584805093,
"min": 1.7356688767895663,
"max": 3.9296203035697426,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1927.7502446174622,
"min": 230.8439606130123,
"max": 2159.3618893027306,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7432043584805093,
"min": 1.7356688767895663,
"max": 3.9296203035697426,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1927.7502446174622,
"min": 230.8439606130123,
"max": 2159.3618893027306,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017021698899366635,
"min": 0.012116209510350019,
"max": 0.02103223738182957,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0510650966980999,
"min": 0.024232419020700037,
"max": 0.05567522269169179,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05208228809965981,
"min": 0.02307099662721157,
"max": 0.06804310337950786,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15624686429897944,
"min": 0.04614199325442314,
"max": 0.1856957755982876,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.744398751899989e-06,
"min": 3.744398751899989e-06,
"max": 0.00029534152655282496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1233196255699967e-05,
"min": 1.1233196255699967e-05,
"max": 0.0008439616686794502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124810000000002,
"min": 0.10124810000000002,
"max": 0.19844717500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037443000000001,
"min": 0.20762305,
"max": 0.58132055,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.228018999999986e-05,
"min": 7.228018999999986e-05,
"max": 0.004922514032499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021684056999999956,
"min": 0.00021684056999999956,
"max": 0.014067895445000003,
"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": "1678288230",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678290701"
},
"total": 2471.425857786,
"count": 1,
"self": 0.4440005309998014,
"children": {
"run_training.setup": {
"total": 0.11018055600004573,
"count": 1,
"self": 0.11018055600004573
},
"TrainerController.start_learning": {
"total": 2470.871676699,
"count": 1,
"self": 4.428326009884131,
"children": {
"TrainerController._reset_env": {
"total": 11.547010806999992,
"count": 1,
"self": 11.547010806999992
},
"TrainerController.advance": {
"total": 2454.7820937591155,
"count": 232273,
"self": 4.7040995600395945,
"children": {
"env_step": {
"total": 1920.9074315580592,
"count": 232273,
"self": 1604.2261780950023,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.7884482999877,
"count": 232273,
"self": 16.53193979001054,
"children": {
"TorchPolicy.evaluate": {
"total": 297.25650850997715,
"count": 222943,
"self": 74.6694295740619,
"children": {
"TorchPolicy.sample_actions": {
"total": 222.58707893591526,
"count": 222943,
"self": 222.58707893591526
}
}
}
}
},
"workers": {
"total": 2.8928051630692835,
"count": 232273,
"self": 0.0,
"children": {
"worker_root": {
"total": 2461.8197018450664,
"count": 232273,
"is_parallel": true,
"self": 1162.0289278290334,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008837370000378542,
"count": 1,
"is_parallel": true,
"self": 0.000326275000077203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005574619999606512,
"count": 2,
"is_parallel": true,
"self": 0.0005574619999606512
}
}
},
"UnityEnvironment.step": {
"total": 0.031701472000008835,
"count": 1,
"is_parallel": true,
"self": 0.0003206150000210073,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019319099999393075,
"count": 1,
"is_parallel": true,
"self": 0.00019319099999393075
},
"communicator.exchange": {
"total": 0.028082568000002084,
"count": 1,
"is_parallel": true,
"self": 0.028082568000002084
},
"steps_from_proto": {
"total": 0.0031050979999918127,
"count": 1,
"is_parallel": true,
"self": 0.00029215600000043196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028129419999913807,
"count": 2,
"is_parallel": true,
"self": 0.0028129419999913807
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1299.790774016033,
"count": 232272,
"is_parallel": true,
"self": 39.161295098148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.69392237490433,
"count": 232272,
"is_parallel": true,
"self": 81.69392237490433
},
"communicator.exchange": {
"total": 1084.46604610108,
"count": 232272,
"is_parallel": true,
"self": 1084.46604610108
},
"steps_from_proto": {
"total": 94.46951044190058,
"count": 232272,
"is_parallel": true,
"self": 40.01369464388932,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.45581579801126,
"count": 464544,
"is_parallel": true,
"self": 54.45581579801126
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.1705626410167,
"count": 232273,
"self": 6.91179787402757,
"children": {
"process_trajectory": {
"total": 170.06043000998915,
"count": 232273,
"self": 168.80782843598905,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2526015740000958,
"count": 10,
"self": 1.2526015740000958
}
}
},
"_update_policy": {
"total": 352.1983347569999,
"count": 97,
"self": 294.2675429219931,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.9307918350068,
"count": 2910,
"self": 57.9307918350068
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.330002856382634e-07,
"count": 1,
"self": 8.330002856382634e-07
},
"TrainerController._save_models": {
"total": 0.11424529000032635,
"count": 1,
"self": 0.00203089600063322,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11221439399969313,
"count": 1,
"self": 0.11221439399969313
}
}
}
}
}
}
}