ppo-Huggy / run_logs /timers.json
lancechen's picture
Huggy
641bb9c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405257225036621,
"min": 1.405257225036621,
"max": 1.427636742591858,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71114.4453125,
"min": 68850.5703125,
"max": 76320.6171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.25585585585586,
"min": 80.05400981996726,
"max": 435.31304347826085,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49537.0,
"min": 48913.0,
"max": 50061.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999650.0,
"min": 49596.0,
"max": 1999650.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999650.0,
"min": 49596.0,
"max": 1999650.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4155526161193848,
"min": 0.1524263322353363,
"max": 2.458395004272461,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1340.6317138671875,
"min": 17.376602172851562,
"max": 1500.334716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7032123703140396,
"min": 1.8987736299372555,
"max": 3.9594471712974966,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2055.282865524292,
"min": 216.46019381284714,
"max": 2353.9351328611374,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7032123703140396,
"min": 1.8987736299372555,
"max": 3.9594471712974966,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2055.282865524292,
"min": 216.46019381284714,
"max": 2353.9351328611374,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01854594608044459,
"min": 0.013655761460540816,
"max": 0.020189259435088994,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05563783824133377,
"min": 0.029025584715418516,
"max": 0.05739708031420984,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059696139478021194,
"min": 0.020601476542651653,
"max": 0.06348361155639091,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1790884184340636,
"min": 0.04120295308530331,
"max": 0.1790884184340636,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.52374882545e-06,
"min": 3.52374882545e-06,
"max": 0.0002952789015737,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.057124647635e-05,
"min": 1.057124647635e-05,
"max": 0.0008441010186330001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117454999999999,
"min": 0.10117454999999999,
"max": 0.1984263,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30352365,
"min": 0.20748295000000003,
"max": 0.5813670000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.8610045e-05,
"min": 6.8610045e-05,
"max": 0.004921472369999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000205830135,
"min": 0.000205830135,
"max": 0.0140702133,
"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": "1676332563",
"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": "1.21.6",
"end_time_seconds": "1676334880"
},
"total": 2316.457709729,
"count": 1,
"self": 0.3964376529997935,
"children": {
"run_training.setup": {
"total": 0.10854767600000059,
"count": 1,
"self": 0.10854767600000059
},
"TrainerController.start_learning": {
"total": 2315.9527244,
"count": 1,
"self": 3.9732600660295248,
"children": {
"TrainerController._reset_env": {
"total": 10.514847422000003,
"count": 1,
"self": 10.514847422000003
},
"TrainerController.advance": {
"total": 2301.3540259419706,
"count": 232535,
"self": 4.299964025949066,
"children": {
"env_step": {
"total": 1786.4653315140506,
"count": 232535,
"self": 1492.7279308961429,
"children": {
"SubprocessEnvManager._take_step": {
"total": 291.0265604198947,
"count": 232535,
"self": 15.127855445966986,
"children": {
"TorchPolicy.evaluate": {
"total": 275.8987049739277,
"count": 222980,
"self": 68.79381181292968,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.10489316099802,
"count": 222980,
"self": 207.10489316099802
}
}
}
}
},
"workers": {
"total": 2.7108401980129315,
"count": 232535,
"self": 0.0,
"children": {
"worker_root": {
"total": 2307.7135698450766,
"count": 232535,
"is_parallel": true,
"self": 1093.0216450201278,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00207302400002618,
"count": 1,
"is_parallel": true,
"self": 0.0003066210000497449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017664029999764352,
"count": 2,
"is_parallel": true,
"self": 0.0017664029999764352
}
}
},
"UnityEnvironment.step": {
"total": 0.030648491000022204,
"count": 1,
"is_parallel": true,
"self": 0.00029517500001929875,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021235200000546683,
"count": 1,
"is_parallel": true,
"self": 0.00021235200000546683
},
"communicator.exchange": {
"total": 0.02930155299998205,
"count": 1,
"is_parallel": true,
"self": 0.02930155299998205
},
"steps_from_proto": {
"total": 0.0008394110000153887,
"count": 1,
"is_parallel": true,
"self": 0.00022071300008974504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006186979999256437,
"count": 2,
"is_parallel": true,
"self": 0.0006186979999256437
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.6919248249487,
"count": 232534,
"is_parallel": true,
"self": 37.60732000195367,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.75283826800387,
"count": 232534,
"is_parallel": true,
"self": 76.75283826800387
},
"communicator.exchange": {
"total": 1009.6412476419955,
"count": 232534,
"is_parallel": true,
"self": 1009.6412476419955
},
"steps_from_proto": {
"total": 90.69051891299569,
"count": 232534,
"is_parallel": true,
"self": 36.66339856794116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.02712034505453,
"count": 465068,
"is_parallel": true,
"self": 54.02712034505453
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.588730401971,
"count": 232535,
"self": 6.498187276776321,
"children": {
"process_trajectory": {
"total": 161.5233743401942,
"count": 232535,
"self": 160.20644676319455,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3169275769996602,
"count": 10,
"self": 1.3169275769996602
}
}
},
"_update_policy": {
"total": 342.5671687850005,
"count": 97,
"self": 285.6182546969973,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.948914088003164,
"count": 2910,
"self": 56.948914088003164
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0745000054157572e-05,
"count": 1,
"self": 1.0745000054157572e-05
},
"TrainerController._save_models": {
"total": 0.11058022499992148,
"count": 1,
"self": 0.0019665590002659883,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1086136659996555,
"count": 1,
"self": 0.1086136659996555
}
}
}
}
}
}
}