ppo-Huggy / run_logs /timers.json
dbailleul's picture
Huggy
6192fc8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4062789678573608,
"min": 1.4062789678573608,
"max": 1.4279687404632568,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69089.078125,
"min": 69089.078125,
"max": 77310.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.60445205479452,
"min": 83.77079796264856,
"max": 387.0615384615385,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49409.0,
"min": 49254.0,
"max": 50318.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49915.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49915.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4083285331726074,
"min": 0.07092244178056717,
"max": 2.454188823699951,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1406.4638671875,
"min": 9.148995399475098,
"max": 1427.893310546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7723341798537398,
"min": 1.8598633175210435,
"max": 3.9491678073056162,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2203.043161034584,
"min": 239.92236796021461,
"max": 2244.5523923635483,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7723341798537398,
"min": 1.8598633175210435,
"max": 3.9491678073056162,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2203.043161034584,
"min": 239.92236796021461,
"max": 2244.5523923635483,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013965387352638775,
"min": 0.013965387352638775,
"max": 0.020780612436404527,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.041896162057916325,
"min": 0.028027691940466563,
"max": 0.057792609607956055,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05971417969299687,
"min": 0.021772973705083132,
"max": 0.05998725462704897,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1791425390789906,
"min": 0.043545947410166264,
"max": 0.1791425390789906,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6775487741833255e-06,
"min": 3.6775487741833255e-06,
"max": 0.000295321276559575,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1032646322549976e-05,
"min": 1.1032646322549976e-05,
"max": 0.00084428086857305,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122581666666668,
"min": 0.10122581666666668,
"max": 0.19844042500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367745,
"min": 0.20759505000000006,
"max": 0.5814269499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.116825166666657e-05,
"min": 7.116825166666657e-05,
"max": 0.0049221772075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021350475499999971,
"min": 0.00021350475499999971,
"max": 0.014073204805000001,
"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": "1699969549",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699972100"
},
"total": 2550.632542281,
"count": 1,
"self": 0.4244836990001204,
"children": {
"run_training.setup": {
"total": 0.04191382999988491,
"count": 1,
"self": 0.04191382999988491
},
"TrainerController.start_learning": {
"total": 2550.166144752,
"count": 1,
"self": 4.943354566961716,
"children": {
"TrainerController._reset_env": {
"total": 9.047301386000072,
"count": 1,
"self": 9.047301386000072
},
"TrainerController.advance": {
"total": 2536.0624740520384,
"count": 232161,
"self": 4.990567728951646,
"children": {
"env_step": {
"total": 2019.1532113169421,
"count": 232161,
"self": 1659.876167971132,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.2615589959196,
"count": 232161,
"self": 17.57504155774518,
"children": {
"TorchPolicy.evaluate": {
"total": 338.6865174381744,
"count": 222856,
"self": 338.6865174381744
}
}
},
"workers": {
"total": 3.015484349890585,
"count": 232161,
"self": 0.0,
"children": {
"worker_root": {
"total": 2542.4664022009783,
"count": 232161,
"is_parallel": true,
"self": 1199.0322958019221,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008318540001255315,
"count": 1,
"is_parallel": true,
"self": 0.00024600400001872913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005858500001068023,
"count": 2,
"is_parallel": true,
"self": 0.0005858500001068023
}
}
},
"UnityEnvironment.step": {
"total": 0.02902763099996264,
"count": 1,
"is_parallel": true,
"self": 0.0003116959999260871,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020332999997663137,
"count": 1,
"is_parallel": true,
"self": 0.00020332999997663137
},
"communicator.exchange": {
"total": 0.02782460200000969,
"count": 1,
"is_parallel": true,
"self": 0.02782460200000969
},
"steps_from_proto": {
"total": 0.0006880030000502302,
"count": 1,
"is_parallel": true,
"self": 0.0001922300002661359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004957729997840943,
"count": 2,
"is_parallel": true,
"self": 0.0004957729997840943
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.4341063990562,
"count": 232160,
"is_parallel": true,
"self": 41.022515630825865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.38505977892441,
"count": 232160,
"is_parallel": true,
"self": 89.38505977892441
},
"communicator.exchange": {
"total": 1121.3498136150888,
"count": 232160,
"is_parallel": true,
"self": 1121.3498136150888
},
"steps_from_proto": {
"total": 91.6767173742171,
"count": 232160,
"is_parallel": true,
"self": 34.31780933930054,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.35890803491657,
"count": 464320,
"is_parallel": true,
"self": 57.35890803491657
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 511.9186950061446,
"count": 232161,
"self": 6.7935177680637935,
"children": {
"process_trajectory": {
"total": 162.2501128030815,
"count": 232161,
"self": 161.0426969640805,
"children": {
"RLTrainer._checkpoint": {
"total": 1.207415839000987,
"count": 10,
"self": 1.207415839000987
}
}
},
"_update_policy": {
"total": 342.87506443499933,
"count": 97,
"self": 279.79361080400145,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.081453630997885,
"count": 2910,
"self": 63.081453630997885
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.439999778085621e-06,
"count": 1,
"self": 1.439999778085621e-06
},
"TrainerController._save_models": {
"total": 0.11301330700007384,
"count": 1,
"self": 0.0029937750000499364,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1100195320000239,
"count": 1,
"self": 0.1100195320000239
}
}
}
}
}
}
}