ppo-Huggy / run_logs /timers.json
nvasko's picture
Huggy
a816e6b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4031909704208374,
"min": 1.4031909704208374,
"max": 1.4265283346176147,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70612.78125,
"min": 68783.84375,
"max": 77558.9296875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.6086956521739,
"min": 74.41176470588235,
"max": 404.98387096774195,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49400.0,
"min": 49219.0,
"max": 50218.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999949.0,
"min": 49965.0,
"max": 1999949.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999949.0,
"min": 49965.0,
"max": 1999949.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.498852252960205,
"min": 0.052338726818561554,
"max": 2.5499236583709717,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1494.3135986328125,
"min": 6.437663555145264,
"max": 1632.23486328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.882918591583054,
"min": 1.8672990798950195,
"max": 4.02773213798642,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2321.9853177666664,
"min": 229.6777868270874,
"max": 2545.6905264258385,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.882918591583054,
"min": 1.8672990798950195,
"max": 4.02773213798642,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2321.9853177666664,
"min": 229.6777868270874,
"max": 2545.6905264258385,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017370980196897614,
"min": 0.012387573565744485,
"max": 0.020675564357467615,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05211294059069284,
"min": 0.02477514713148897,
"max": 0.05779982243596654,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05802762458721797,
"min": 0.021792950015515088,
"max": 0.06419496399660905,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1740828737616539,
"min": 0.043585900031030175,
"max": 0.17998531945049764,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.90479869843334e-06,
"min": 3.90479869843334e-06,
"max": 0.0002953734015421999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1714396095300019e-05,
"min": 1.1714396095300019e-05,
"max": 0.00084413236862255,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130156666666668,
"min": 0.10130156666666668,
"max": 0.19845780000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039047,
"min": 0.20777290000000004,
"max": 0.5813774500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.494817666666677e-05,
"min": 7.494817666666677e-05,
"max": 0.004923044219999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022484453000000033,
"min": 0.00022484453000000033,
"max": 0.014070734755,
"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": "1701311261",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701313913"
},
"total": 2651.591597941,
"count": 1,
"self": 0.44461026699991635,
"children": {
"run_training.setup": {
"total": 0.07108128900000565,
"count": 1,
"self": 0.07108128900000565
},
"TrainerController.start_learning": {
"total": 2651.075906385,
"count": 1,
"self": 4.860828504089568,
"children": {
"TrainerController._reset_env": {
"total": 3.531836627999951,
"count": 1,
"self": 3.531836627999951
},
"TrainerController.advance": {
"total": 2642.5782240989106,
"count": 233140,
"self": 5.3603522829066605,
"children": {
"env_step": {
"total": 2095.600306022062,
"count": 233140,
"self": 1731.8533711511218,
"children": {
"SubprocessEnvManager._take_step": {
"total": 360.48668693899117,
"count": 233140,
"self": 18.572628107077946,
"children": {
"TorchPolicy.evaluate": {
"total": 341.9140588319132,
"count": 222982,
"self": 341.9140588319132
}
}
},
"workers": {
"total": 3.260247931948925,
"count": 233140,
"self": 0.0,
"children": {
"worker_root": {
"total": 2643.204630898958,
"count": 233140,
"is_parallel": true,
"self": 1244.4043151648602,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009127490000082616,
"count": 1,
"is_parallel": true,
"self": 0.00026767299999619354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006450760000120681,
"count": 2,
"is_parallel": true,
"self": 0.0006450760000120681
}
}
},
"UnityEnvironment.step": {
"total": 0.046550358999979835,
"count": 1,
"is_parallel": true,
"self": 0.00033200199999328106,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021443499997531035,
"count": 1,
"is_parallel": true,
"self": 0.00021443499997531035
},
"communicator.exchange": {
"total": 0.04524074300002212,
"count": 1,
"is_parallel": true,
"self": 0.04524074300002212
},
"steps_from_proto": {
"total": 0.0007631789999891225,
"count": 1,
"is_parallel": true,
"self": 0.0002277139999478095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000535465000041313,
"count": 2,
"is_parallel": true,
"self": 0.000535465000041313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1398.8003157340977,
"count": 233139,
"is_parallel": true,
"self": 42.79482677494184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.7276801960345,
"count": 233139,
"is_parallel": true,
"self": 93.7276801960345
},
"communicator.exchange": {
"total": 1164.2964167620898,
"count": 233139,
"is_parallel": true,
"self": 1164.2964167620898
},
"steps_from_proto": {
"total": 97.98139200103145,
"count": 233139,
"is_parallel": true,
"self": 36.68581220410181,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.295579796929644,
"count": 466278,
"is_parallel": true,
"self": 61.295579796929644
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 541.617565793942,
"count": 233140,
"self": 7.309299199931502,
"children": {
"process_trajectory": {
"total": 174.45023024401218,
"count": 233140,
"self": 173.2146214690129,
"children": {
"RLTrainer._checkpoint": {
"total": 1.235608774999264,
"count": 10,
"self": 1.235608774999264
}
}
},
"_update_policy": {
"total": 359.8580363499983,
"count": 97,
"self": 294.6304191619852,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.22761718801314,
"count": 2910,
"self": 65.22761718801314
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.66999778029276e-07,
"count": 1,
"self": 9.66999778029276e-07
},
"TrainerController._save_models": {
"total": 0.10501618700027393,
"count": 1,
"self": 0.001727875000142376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10328831200013155,
"count": 1,
"self": 0.10328831200013155
}
}
}
}
}
}
}