ppo-Huggy / run_logs /timers.json
TeSeMeNe's picture
Huggy
61f4eca verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4103622436523438,
"min": 1.4103622436523438,
"max": 1.4311249256134033,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69707.15625,
"min": 68213.5546875,
"max": 75773.2421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 115.85981308411215,
"min": 96.11456310679611,
"max": 409.71311475409834,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49588.0,
"min": 48880.0,
"max": 50203.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999881.0,
"min": 49627.0,
"max": 1999881.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999881.0,
"min": 49627.0,
"max": 1999881.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.335299491882324,
"min": 0.016351565718650818,
"max": 2.4193646907806396,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 999.5081787109375,
"min": 1.9785393476486206,
"max": 1203.3505859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.613895037046103,
"min": 1.8211272952477795,
"max": 3.880858331845492,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1546.747075855732,
"min": 220.3564027249813,
"max": 1907.3530255556107,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.613895037046103,
"min": 1.8211272952477795,
"max": 3.880858331845492,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1546.747075855732,
"min": 220.3564027249813,
"max": 1907.3530255556107,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017480305956754212,
"min": 0.014177894879442949,
"max": 0.01963137733206774,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034960611913508424,
"min": 0.028355789758885898,
"max": 0.056384570719228574,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.047460427818199,
"min": 0.02239094109584888,
"max": 0.05617028002937635,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.094920855636398,
"min": 0.04478188219169776,
"max": 0.16661702394485473,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.503923498724989e-06,
"min": 4.503923498724989e-06,
"max": 0.00029528265157245003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.007846997449977e-06,
"min": 9.007846997449977e-06,
"max": 0.00084411946862685,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101501275,
"min": 0.101501275,
"max": 0.19842755000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20300255,
"min": 0.20300255,
"max": 0.5813731500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.491362249999984e-05,
"min": 8.491362249999984e-05,
"max": 0.004921534745,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016982724499999967,
"min": 0.00016982724499999967,
"max": 0.014070520185000003,
"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": "1730535549",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730538309"
},
"total": 2759.979339937,
"count": 1,
"self": 0.4764125020001302,
"children": {
"run_training.setup": {
"total": 0.06314826999994239,
"count": 1,
"self": 0.06314826999994239
},
"TrainerController.start_learning": {
"total": 2759.439779165,
"count": 1,
"self": 5.6425771249028,
"children": {
"TrainerController._reset_env": {
"total": 6.424423587999968,
"count": 1,
"self": 6.424423587999968
},
"TrainerController.advance": {
"total": 2747.253999003097,
"count": 231130,
"self": 5.276040265942811,
"children": {
"env_step": {
"total": 2203.7046814980467,
"count": 231130,
"self": 1730.9534492820394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 469.29394488802336,
"count": 231130,
"self": 18.05754329493095,
"children": {
"TorchPolicy.evaluate": {
"total": 451.2364015930924,
"count": 223028,
"self": 451.2364015930924
}
}
},
"workers": {
"total": 3.457287327983977,
"count": 231130,
"self": 0.0,
"children": {
"worker_root": {
"total": 2751.21179742795,
"count": 231130,
"is_parallel": true,
"self": 1346.8858538968575,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010530890000381987,
"count": 1,
"is_parallel": true,
"self": 0.0003270619999966584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007260270000415403,
"count": 2,
"is_parallel": true,
"self": 0.0007260270000415403
}
}
},
"UnityEnvironment.step": {
"total": 0.031970918000070014,
"count": 1,
"is_parallel": true,
"self": 0.0004218280000714003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001850229999718067,
"count": 1,
"is_parallel": true,
"self": 0.0001850229999718067
},
"communicator.exchange": {
"total": 0.03056706600000325,
"count": 1,
"is_parallel": true,
"self": 0.03056706600000325
},
"steps_from_proto": {
"total": 0.0007970010000235561,
"count": 1,
"is_parallel": true,
"self": 0.00020782000001418055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005891810000093756,
"count": 2,
"is_parallel": true,
"self": 0.0005891810000093756
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1404.3259435310924,
"count": 231129,
"is_parallel": true,
"self": 42.176015684955246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.74404741201397,
"count": 231129,
"is_parallel": true,
"self": 86.74404741201397
},
"communicator.exchange": {
"total": 1173.9911793580775,
"count": 231129,
"is_parallel": true,
"self": 1173.9911793580775
},
"steps_from_proto": {
"total": 101.41470107604573,
"count": 231129,
"is_parallel": true,
"self": 35.03010782920194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.38459324684379,
"count": 462258,
"is_parallel": true,
"self": 66.38459324684379
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 538.2732772391075,
"count": 231130,
"self": 8.380269245071531,
"children": {
"process_trajectory": {
"total": 178.2997272720362,
"count": 231130,
"self": 175.60438980803644,
"children": {
"RLTrainer._checkpoint": {
"total": 2.695337463999749,
"count": 20,
"self": 2.695337463999749
}
}
},
"_update_policy": {
"total": 351.5932807219998,
"count": 96,
"self": 280.11227205,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.4810086719998,
"count": 2880,
"self": 71.4810086719998
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2390000847517513e-06,
"count": 1,
"self": 1.2390000847517513e-06
},
"TrainerController._save_models": {
"total": 0.11877821000007316,
"count": 1,
"self": 0.0023431019999407,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11643510800013246,
"count": 1,
"self": 0.11643510800013246
}
}
}
}
}
}
}