ppo-Huggy / run_logs /timers.json
adi-vc's picture
Huggy
fca3452
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404048204421997,
"min": 1.404048204421997,
"max": 1.429051399230957,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70361.0703125,
"min": 68357.3125,
"max": 75205.4609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.05747126436782,
"min": 75.18873668188736,
"max": 412.64462809917353,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49364.0,
"min": 48806.0,
"max": 50330.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999936.0,
"min": 49766.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999936.0,
"min": 49766.0,
"max": 1999936.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.500925302505493,
"min": 0.11658858507871628,
"max": 2.5155646800994873,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1523.0634765625,
"min": 13.990630149841309,
"max": 1626.3497314453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.814782923371921,
"min": 1.9038242960969607,
"max": 4.041553812451882,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2323.2028003335,
"min": 228.45891553163528,
"max": 2547.0863239765167,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.814782923371921,
"min": 1.9038242960969607,
"max": 4.041553812451882,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2323.2028003335,
"min": 228.45891553163528,
"max": 2547.0863239765167,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017410727414810225,
"min": 0.014518803191701107,
"max": 0.020167396248467008,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05223218224443068,
"min": 0.029037606383402213,
"max": 0.060502188745401024,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06272252520753278,
"min": 0.02120087267830968,
"max": 0.06272252520753278,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18816757562259834,
"min": 0.04240174535661936,
"max": 0.18816757562259834,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.856698714466664e-06,
"min": 3.856698714466664e-06,
"max": 0.00029535240154919995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1570096143399993e-05,
"min": 1.1570096143399993e-05,
"max": 0.000844074018642,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128553333333334,
"min": 0.10128553333333334,
"max": 0.19845079999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30385660000000003,
"min": 0.20770085000000005,
"max": 0.5813580000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.414811333333333e-05,
"min": 7.414811333333333e-05,
"max": 0.00492269492,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022244433999999997,
"min": 0.00022244433999999997,
"max": 0.014069764200000001,
"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": "1693945962",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/data2/home/adityacv/.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": "1693948984"
},
"total": 3022.2740160160465,
"count": 1,
"self": 0.3741842571180314,
"children": {
"run_training.setup": {
"total": 0.02314328297507018,
"count": 1,
"self": 0.02314328297507018
},
"TrainerController.start_learning": {
"total": 3021.8766884759534,
"count": 1,
"self": 3.0179718997096643,
"children": {
"TrainerController._reset_env": {
"total": 2.9254076880170032,
"count": 1,
"self": 2.9254076880170032
},
"TrainerController.advance": {
"total": 3015.756692854222,
"count": 233205,
"self": 3.1473098678980023,
"children": {
"env_step": {
"total": 2632.8950017073657,
"count": 233205,
"self": 2441.6279042395763,
"children": {
"SubprocessEnvManager._take_step": {
"total": 189.23856796696782,
"count": 233205,
"self": 11.640125254634768,
"children": {
"TorchPolicy.evaluate": {
"total": 177.59844271233305,
"count": 222934,
"self": 177.59844271233305
}
}
},
"workers": {
"total": 2.0285295008216053,
"count": 233205,
"self": 0.0,
"children": {
"worker_root": {
"total": 3010.4449953350704,
"count": 233205,
"is_parallel": true,
"self": 877.2470138249919,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001770374015904963,
"count": 1,
"is_parallel": true,
"self": 0.00044163898564875126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013287350302562118,
"count": 2,
"is_parallel": true,
"self": 0.0013287350302562118
}
}
},
"UnityEnvironment.step": {
"total": 0.03451242297887802,
"count": 1,
"is_parallel": true,
"self": 0.00028008315712213516,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003149639815092087,
"count": 1,
"is_parallel": true,
"self": 0.0003149639815092087
},
"communicator.exchange": {
"total": 0.03343575191684067,
"count": 1,
"is_parallel": true,
"self": 0.03343575191684067
},
"steps_from_proto": {
"total": 0.0004816239234060049,
"count": 1,
"is_parallel": true,
"self": 0.00013091485016047955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00035070907324552536,
"count": 2,
"is_parallel": true,
"self": 0.00035070907324552536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2133.1979815100785,
"count": 233204,
"is_parallel": true,
"self": 66.89526640367694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 128.12727839371655,
"count": 233204,
"is_parallel": true,
"self": 128.12727839371655
},
"communicator.exchange": {
"total": 1780.1346850319533,
"count": 233204,
"is_parallel": true,
"self": 1780.1346850319533
},
"steps_from_proto": {
"total": 158.04075168073177,
"count": 233204,
"is_parallel": true,
"self": 57.09882215282414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 100.94192952790763,
"count": 466408,
"is_parallel": true,
"self": 100.94192952790763
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 379.7143812789582,
"count": 233205,
"self": 4.920457730186172,
"children": {
"process_trajectory": {
"total": 99.83081132709049,
"count": 233205,
"self": 98.517841309309,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3129700177814811,
"count": 10,
"self": 1.3129700177814811
}
}
},
"_update_policy": {
"total": 274.9631122216815,
"count": 97,
"self": 231.21034864429384,
"children": {
"TorchPPOOptimizer.update": {
"total": 43.75276357738767,
"count": 2910,
"self": 43.75276357738767
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.479699656367302e-07,
"count": 1,
"self": 9.479699656367302e-07
},
"TrainerController._save_models": {
"total": 0.17661508603487164,
"count": 1,
"self": 0.002106145955622196,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17450894007924944,
"count": 1,
"self": 0.17450894007924944
}
}
}
}
}
}
}