ppo-Huggy / run_logs /timers.json
CAVJ's picture
Huggy
20aabaa verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4040467739105225,
"min": 1.4040467739105225,
"max": 1.431562900543213,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69863.9609375,
"min": 68773.984375,
"max": 77240.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 115.57109557109557,
"min": 97.85828343313374,
"max": 407.9349593495935,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49580.0,
"min": 49002.0,
"max": 50210.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49816.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49816.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3184289932250977,
"min": 0.16313832998275757,
"max": 2.402325391769409,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 994.6060180664062,
"min": 19.902875900268555,
"max": 1165.130859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.662714127338294,
"min": 1.8896450678833197,
"max": 3.8429676762460607,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1571.304360628128,
"min": 230.53669828176498,
"max": 1840.1680231690407,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.662714127338294,
"min": 1.8896450678833197,
"max": 3.8429676762460607,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1571.304360628128,
"min": 230.53669828176498,
"max": 1840.1680231690407,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016486399362717445,
"min": 0.013258343688600386,
"max": 0.020207974922717163,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03297279872543489,
"min": 0.02651668737720077,
"max": 0.0552600122988224,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.044096373518308,
"min": 0.02087576078871886,
"max": 0.06123677715659141,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.088192747036616,
"min": 0.0434642095118761,
"max": 0.18149581377704938,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.248023584024989e-06,
"min": 4.248023584024989e-06,
"max": 0.000295333126555625,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.496047168049978e-06,
"min": 8.496047168049978e-06,
"max": 0.0008439687186770997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10141597500000002,
"min": 0.10141597500000002,
"max": 0.19844437499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20283195000000004,
"min": 0.20283195000000004,
"max": 0.5813229,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.065715249999986e-05,
"min": 8.065715249999986e-05,
"max": 0.004922374312499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016131430499999972,
"min": 0.00016131430499999972,
"max": 0.014068012709999998,
"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": "1740089704",
"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": "1740092244"
},
"total": 2540.105439692,
"count": 1,
"self": 0.8087321929997415,
"children": {
"run_training.setup": {
"total": 0.03009784099992885,
"count": 1,
"self": 0.03009784099992885
},
"TrainerController.start_learning": {
"total": 2539.266609658,
"count": 1,
"self": 4.77085825004724,
"children": {
"TrainerController._reset_env": {
"total": 3.1266442439999764,
"count": 1,
"self": 3.1266442439999764
},
"TrainerController.advance": {
"total": 2531.1984026559526,
"count": 231023,
"self": 5.0792905499552035,
"children": {
"env_step": {
"total": 2056.8096958829833,
"count": 231023,
"self": 1609.9770101289791,
"children": {
"SubprocessEnvManager._take_step": {
"total": 443.9268032819764,
"count": 231023,
"self": 16.844315464052215,
"children": {
"TorchPolicy.evaluate": {
"total": 427.0824878179242,
"count": 222985,
"self": 427.0824878179242
}
}
},
"workers": {
"total": 2.905882472027656,
"count": 231023,
"self": 0.0,
"children": {
"worker_root": {
"total": 2531.201090882899,
"count": 231023,
"is_parallel": true,
"self": 1221.9590975138858,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011378309999372505,
"count": 1,
"is_parallel": true,
"self": 0.00041584699988561624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007219840000516342,
"count": 2,
"is_parallel": true,
"self": 0.0007219840000516342
}
}
},
"UnityEnvironment.step": {
"total": 0.05093680499999209,
"count": 1,
"is_parallel": true,
"self": 0.00035934699985773477,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021893400003136776,
"count": 1,
"is_parallel": true,
"self": 0.00021893400003136776
},
"communicator.exchange": {
"total": 0.04959392000000662,
"count": 1,
"is_parallel": true,
"self": 0.04959392000000662
},
"steps_from_proto": {
"total": 0.0007646040000963694,
"count": 1,
"is_parallel": true,
"self": 0.00022609500001635752,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005385090000800119,
"count": 2,
"is_parallel": true,
"self": 0.0005385090000800119
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1309.241993369013,
"count": 231022,
"is_parallel": true,
"self": 39.12979384007667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.10146455997949,
"count": 231022,
"is_parallel": true,
"self": 85.10146455997949
},
"communicator.exchange": {
"total": 1093.3407874699978,
"count": 231022,
"is_parallel": true,
"self": 1093.3407874699978
},
"steps_from_proto": {
"total": 91.669947498959,
"count": 231022,
"is_parallel": true,
"self": 33.97017522706244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.69977227189656,
"count": 462044,
"is_parallel": true,
"self": 57.69977227189656
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.3094162230143,
"count": 231023,
"self": 7.050455169096949,
"children": {
"process_trajectory": {
"total": 158.79659672591777,
"count": 231023,
"self": 157.41103601291684,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3855607130009275,
"count": 10,
"self": 1.3855607130009275
}
}
},
"_update_policy": {
"total": 303.4623643279996,
"count": 96,
"self": 239.2387220249949,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.22364230300468,
"count": 2880,
"self": 64.22364230300468
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9260000954091083e-06,
"count": 1,
"self": 1.9260000954091083e-06
},
"TrainerController._save_models": {
"total": 0.17070258200010358,
"count": 1,
"self": 0.0040027700001701305,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16669981199993344,
"count": 1,
"self": 0.16669981199993344
}
}
}
}
}
}
}