ppo-Huggy / run_logs /timers.json
AE1999's picture
Huggy
63a0042 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4012963771820068,
"min": 1.4012963771820068,
"max": 1.4294337034225464,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70881.7734375,
"min": 68354.59375,
"max": 76588.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.16814159292035,
"min": 85.50782608695653,
"max": 416.85,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49250.0,
"min": 48935.0,
"max": 50087.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49410.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49410.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3707425594329834,
"min": 0.025072962045669556,
"max": 2.4455928802490234,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1339.4696044921875,
"min": 2.98368239402771,
"max": 1363.450439453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.690949868839399,
"min": 1.8197762793352623,
"max": 3.9752999393813377,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2085.3866758942604,
"min": 216.55337724089622,
"max": 2089.5448589920998,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.690949868839399,
"min": 1.8197762793352623,
"max": 3.9752999393813377,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2085.3866758942604,
"min": 216.55337724089622,
"max": 2089.5448589920998,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016768345328617013,
"min": 0.012609485850286244,
"max": 0.018957815409764104,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05030503598585104,
"min": 0.02521897170057249,
"max": 0.05497720890440785,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05818253229889605,
"min": 0.02240691790357232,
"max": 0.06689632615695397,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17454759689668814,
"min": 0.04481383580714464,
"max": 0.19819513882199924,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2147989284333383e-06,
"min": 3.2147989284333383e-06,
"max": 0.0002953668015444,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.644396785300015e-06,
"min": 9.644396785300015e-06,
"max": 0.0008442543185819,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107156666666671,
"min": 0.10107156666666671,
"max": 0.19845559999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032147000000001,
"min": 0.20738345000000002,
"max": 0.5814180999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.347117666666673e-05,
"min": 6.347117666666673e-05,
"max": 0.0049229344399999994,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001904135300000002,
"min": 0.0001904135300000002,
"max": 0.01407276319,
"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": "1723057556",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723060027"
},
"total": 2470.52990287,
"count": 1,
"self": 0.4899070770002254,
"children": {
"run_training.setup": {
"total": 0.06634364599995024,
"count": 1,
"self": 0.06634364599995024
},
"TrainerController.start_learning": {
"total": 2469.973652147,
"count": 1,
"self": 4.520500649156929,
"children": {
"TrainerController._reset_env": {
"total": 3.0985014240000055,
"count": 1,
"self": 3.0985014240000055
},
"TrainerController.advance": {
"total": 2462.2257756708427,
"count": 231557,
"self": 4.791928782112791,
"children": {
"env_step": {
"total": 1949.6872105168836,
"count": 231557,
"self": 1605.297755064041,
"children": {
"SubprocessEnvManager._take_step": {
"total": 341.34614142493774,
"count": 231557,
"self": 17.639154646949464,
"children": {
"TorchPolicy.evaluate": {
"total": 323.7069867779883,
"count": 222928,
"self": 323.7069867779883
}
}
},
"workers": {
"total": 3.0433140279048985,
"count": 231557,
"self": 0.0,
"children": {
"worker_root": {
"total": 2462.4632262479527,
"count": 231557,
"is_parallel": true,
"self": 1168.0476936519397,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009324709999418701,
"count": 1,
"is_parallel": true,
"self": 0.00023721099978502025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006952600001568499,
"count": 2,
"is_parallel": true,
"self": 0.0006952600001568499
}
}
},
"UnityEnvironment.step": {
"total": 0.04703803899997183,
"count": 1,
"is_parallel": true,
"self": 0.00040095700001074874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022186399996826367,
"count": 1,
"is_parallel": true,
"self": 0.00022186399996826367
},
"communicator.exchange": {
"total": 0.04565962599986051,
"count": 1,
"is_parallel": true,
"self": 0.04565962599986051
},
"steps_from_proto": {
"total": 0.0007555920001323102,
"count": 1,
"is_parallel": true,
"self": 0.00020239599984961387,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005531960002826963,
"count": 2,
"is_parallel": true,
"self": 0.0005531960002826963
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1294.415532596013,
"count": 231556,
"is_parallel": true,
"self": 39.366461318198844,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.03288313891471,
"count": 231556,
"is_parallel": true,
"self": 82.03288313891471
},
"communicator.exchange": {
"total": 1079.7723436839467,
"count": 231556,
"is_parallel": true,
"self": 1079.7723436839467
},
"steps_from_proto": {
"total": 93.24384445495275,
"count": 231556,
"is_parallel": true,
"self": 32.99304742607501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.25079702887774,
"count": 463112,
"is_parallel": true,
"self": 60.25079702887774
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 507.7466363718461,
"count": 231557,
"self": 7.014415580664263,
"children": {
"process_trajectory": {
"total": 157.47182769018514,
"count": 231557,
"self": 156.07913801018572,
"children": {
"RLTrainer._checkpoint": {
"total": 1.392689679999421,
"count": 10,
"self": 1.392689679999421
}
}
},
"_update_policy": {
"total": 343.2603931009967,
"count": 97,
"self": 277.286499818013,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.97389328298368,
"count": 2910,
"self": 65.97389328298368
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0550002116360702e-06,
"count": 1,
"self": 1.0550002116360702e-06
},
"TrainerController._save_models": {
"total": 0.1288733480000701,
"count": 1,
"self": 0.002412394999737444,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12646095300033267,
"count": 1,
"self": 0.12646095300033267
}
}
}
}
}
}
}