ppo-Huggy / run_logs /timers.json
binganao's picture
Huggy
6061811 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042507410049438,
"min": 1.4042507410049438,
"max": 1.4287440776824951,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70785.46875,
"min": 68301.75,
"max": 77150.1640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 122.6019656019656,
"min": 100.98979591836735,
"max": 404.216,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49899.0,
"min": 49237.0,
"max": 50527.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999625.0,
"min": 49903.0,
"max": 1999625.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999625.0,
"min": 49903.0,
"max": 1999625.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2223777770996094,
"min": 0.09469681233167648,
"max": 2.3669514656066895,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 904.5077514648438,
"min": 11.74240493774414,
"max": 1118.6693115234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.343272159082005,
"min": 1.938809814592523,
"max": 3.8424064937227462,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1360.711768746376,
"min": 240.41241700947285,
"max": 1802.9707844853401,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.343272159082005,
"min": 1.938809814592523,
"max": 3.8424064937227462,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1360.711768746376,
"min": 240.41241700947285,
"max": 1802.9707844853401,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015543128757659966,
"min": 0.013224267020996194,
"max": 0.019190652281152628,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03108625751531993,
"min": 0.026448534041992388,
"max": 0.0575372248268953,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04390896366288265,
"min": 0.020558389959235986,
"max": 0.058661920763552186,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0878179273257653,
"min": 0.04111677991847197,
"max": 0.17013350725173948,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.397798534100011e-06,
"min": 4.397798534100011e-06,
"max": 0.00029532540155820003,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.795597068200023e-06,
"min": 8.795597068200023e-06,
"max": 0.0008438053687315498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014659,
"min": 0.1014659,
"max": 0.19844179999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029318,
"min": 0.2029318,
"max": 0.58126845,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.314841000000016e-05,
"min": 8.314841000000016e-05,
"max": 0.004922245820000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016629682000000032,
"min": 0.00016629682000000032,
"max": 0.014065295655,
"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": "1713590716",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713593120"
},
"total": 2403.198367317,
"count": 1,
"self": 0.44862400299962246,
"children": {
"run_training.setup": {
"total": 0.05579853700004378,
"count": 1,
"self": 0.05579853700004378
},
"TrainerController.start_learning": {
"total": 2402.693944777,
"count": 1,
"self": 4.185318399958305,
"children": {
"TrainerController._reset_env": {
"total": 3.0373458710000136,
"count": 1,
"self": 3.0373458710000136
},
"TrainerController.advance": {
"total": 2395.354118101042,
"count": 230922,
"self": 4.729082739077057,
"children": {
"env_step": {
"total": 1909.2166306729555,
"count": 230922,
"self": 1586.3720431699296,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.9648281920437,
"count": 230922,
"self": 16.730839077983376,
"children": {
"TorchPolicy.evaluate": {
"total": 303.2339891140603,
"count": 222996,
"self": 303.2339891140603
}
}
},
"workers": {
"total": 2.8797593109822515,
"count": 230922,
"self": 0.0,
"children": {
"worker_root": {
"total": 2395.610972133044,
"count": 230922,
"is_parallel": true,
"self": 1112.680725122037,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009471989999951802,
"count": 1,
"is_parallel": true,
"self": 0.0002447339999775977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007024650000175825,
"count": 2,
"is_parallel": true,
"self": 0.0007024650000175825
}
}
},
"UnityEnvironment.step": {
"total": 0.028527633000010155,
"count": 1,
"is_parallel": true,
"self": 0.0004130869999698916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020797100000891078,
"count": 1,
"is_parallel": true,
"self": 0.00020797100000891078
},
"communicator.exchange": {
"total": 0.02716015100003233,
"count": 1,
"is_parallel": true,
"self": 0.02716015100003233
},
"steps_from_proto": {
"total": 0.0007464239999990241,
"count": 1,
"is_parallel": true,
"self": 0.00020111699996050447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005453070000385196,
"count": 2,
"is_parallel": true,
"self": 0.0005453070000385196
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1282.930247011007,
"count": 230921,
"is_parallel": true,
"self": 39.54475801696549,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.38366720807011,
"count": 230921,
"is_parallel": true,
"self": 82.38366720807011
},
"communicator.exchange": {
"total": 1070.1232123010307,
"count": 230921,
"is_parallel": true,
"self": 1070.1232123010307
},
"steps_from_proto": {
"total": 90.87860948494068,
"count": 230921,
"is_parallel": true,
"self": 32.46484582097895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.41376366396173,
"count": 461842,
"is_parallel": true,
"self": 58.41376366396173
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 481.40840468900916,
"count": 230922,
"self": 6.792751745958299,
"children": {
"process_trajectory": {
"total": 146.23041458604956,
"count": 230922,
"self": 144.4611709380494,
"children": {
"RLTrainer._checkpoint": {
"total": 1.769243648000156,
"count": 10,
"self": 1.769243648000156
}
}
},
"_update_policy": {
"total": 328.3852383570013,
"count": 96,
"self": 265.1262183290012,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.25902002800012,
"count": 2880,
"self": 63.25902002800012
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.189998309011571e-07,
"count": 1,
"self": 9.189998309011571e-07
},
"TrainerController._save_models": {
"total": 0.11716148599998633,
"count": 1,
"self": 0.0021766459999525978,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11498484000003373,
"count": 1,
"self": 0.11498484000003373
}
}
}
}
}
}
}