ppo-Huggy / run_logs /timers.json
simrox's picture
Huggy
24bdca1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4069000482559204,
"min": 1.4069000482559204,
"max": 1.426803708076477,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70574.328125,
"min": 68848.1796875,
"max": 76648.453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.99684044233807,
"min": 71.65602322206095,
"max": 423.1186440677966,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49372.0,
"min": 49152.0,
"max": 49928.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999937.0,
"min": 49761.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999937.0,
"min": 49761.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5377655029296875,
"min": -0.03863583132624626,
"max": 2.5377655029296875,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1606.405517578125,
"min": -4.520392417907715,
"max": 1677.4212646484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9924764430730075,
"min": 1.7425161098313129,
"max": 4.026978160499446,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2527.237588465214,
"min": 203.8743848502636,
"max": 2665.8595422506332,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9924764430730075,
"min": 1.7425161098313129,
"max": 4.026978160499446,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2527.237588465214,
"min": 203.8743848502636,
"max": 2665.8595422506332,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018540187347652035,
"min": 0.012751869411537577,
"max": 0.022340913380806647,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0556205620429561,
"min": 0.025503738823075155,
"max": 0.057796652026202835,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06495803735322421,
"min": 0.02382887744655212,
"max": 0.06495803735322421,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19487411205967264,
"min": 0.04765775489310424,
"max": 0.19487411205967264,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.917598694166673e-06,
"min": 3.917598694166673e-06,
"max": 0.00029537985154005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1752796082500019e-05,
"min": 1.1752796082500019e-05,
"max": 0.0008444286185237999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130583333333336,
"min": 0.10130583333333336,
"max": 0.19845995000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30391750000000006,
"min": 0.207742,
"max": 0.5814762,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.516108333333346e-05,
"min": 7.516108333333346e-05,
"max": 0.004923151505000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002254832500000004,
"min": 0.0002254832500000004,
"max": 0.014075662380000003,
"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": "1673602936",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673605379"
},
"total": 2443.437066035,
"count": 1,
"self": 0.4436808890000066,
"children": {
"run_training.setup": {
"total": 0.11696536299996296,
"count": 1,
"self": 0.11696536299996296
},
"TrainerController.start_learning": {
"total": 2442.876419783,
"count": 1,
"self": 4.442810880973411,
"children": {
"TrainerController._reset_env": {
"total": 11.26835728099968,
"count": 1,
"self": 11.26835728099968
},
"TrainerController.advance": {
"total": 2427.0357145260277,
"count": 233229,
"self": 4.567031231992132,
"children": {
"env_step": {
"total": 1925.5912892540596,
"count": 233229,
"self": 1621.6066694578153,
"children": {
"SubprocessEnvManager._take_step": {
"total": 301.0011798651344,
"count": 233229,
"self": 15.92559685119204,
"children": {
"TorchPolicy.evaluate": {
"total": 285.0755830139424,
"count": 222935,
"self": 70.83534483586027,
"children": {
"TorchPolicy.sample_actions": {
"total": 214.2402381780821,
"count": 222935,
"self": 214.2402381780821
}
}
}
}
},
"workers": {
"total": 2.9834399311098423,
"count": 233229,
"self": 0.0,
"children": {
"worker_root": {
"total": 2434.105533264928,
"count": 233229,
"is_parallel": true,
"self": 1106.3990561828568,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0023112670000955404,
"count": 1,
"is_parallel": true,
"self": 0.00034129699952245574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019699700005730847,
"count": 2,
"is_parallel": true,
"self": 0.0019699700005730847
}
}
},
"UnityEnvironment.step": {
"total": 0.030116508999981306,
"count": 1,
"is_parallel": true,
"self": 0.00028921799957970507,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018980400000145892,
"count": 1,
"is_parallel": true,
"self": 0.00018980400000145892
},
"communicator.exchange": {
"total": 0.028706323000278644,
"count": 1,
"is_parallel": true,
"self": 0.028706323000278644
},
"steps_from_proto": {
"total": 0.0009311640001214982,
"count": 1,
"is_parallel": true,
"self": 0.0004256490001353086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005055149999861897,
"count": 2,
"is_parallel": true,
"self": 0.0005055149999861897
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1327.7064770820712,
"count": 233228,
"is_parallel": true,
"self": 37.277199418958844,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.56618924305758,
"count": 233228,
"is_parallel": true,
"self": 85.56618924305758
},
"communicator.exchange": {
"total": 1102.894638981104,
"count": 233228,
"is_parallel": true,
"self": 1102.894638981104
},
"steps_from_proto": {
"total": 101.96844943895076,
"count": 233228,
"is_parallel": true,
"self": 44.339237949932794,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.62921148901796,
"count": 466456,
"is_parallel": true,
"self": 57.62921148901796
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 496.877394039976,
"count": 233229,
"self": 6.500457676799215,
"children": {
"process_trajectory": {
"total": 164.44468020017575,
"count": 233229,
"self": 163.12242386517664,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3222563349991105,
"count": 10,
"self": 1.3222563349991105
}
}
},
"_update_policy": {
"total": 325.93225616300106,
"count": 97,
"self": 271.7118240710147,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.22043209198637,
"count": 2910,
"self": 54.22043209198637
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.839997462928295e-07,
"count": 1,
"self": 8.839997462928295e-07
},
"TrainerController._save_models": {
"total": 0.12953621099950396,
"count": 1,
"self": 0.002152379999643017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12738383099986095,
"count": 1,
"self": 0.12738383099986095
}
}
}
}
}
}
}