ppo-Huggy / run_logs /timers.json
Seungwoo Kim
Huggy
9e77193
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3970979452133179,
"min": 1.3970979452133179,
"max": 1.4257476329803467,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70114.7578125,
"min": 68786.296875,
"max": 77344.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.23338485316847,
"min": 72.87887740029542,
"max": 390.171875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49323.0,
"min": 48711.0,
"max": 50289.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49654.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49654.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.52142333984375,
"min": 0.013527574017643929,
"max": 2.52142333984375,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1631.36083984375,
"min": 1.7180018424987793,
"max": 1645.5078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9320830773717654,
"min": 1.8379211578312822,
"max": 3.9974681667463723,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2544.057751059532,
"min": 233.41598704457283,
"max": 2562.3280004262924,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9320830773717654,
"min": 1.8379211578312822,
"max": 3.9974681667463723,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2544.057751059532,
"min": 233.41598704457283,
"max": 2562.3280004262924,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013937706375145353,
"min": 0.013230125249780636,
"max": 0.0227744520874694,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04181311912543606,
"min": 0.026460250499561272,
"max": 0.05747116285492666,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06086401918696033,
"min": 0.022783264983445406,
"max": 0.06271232490738232,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18259205756088098,
"min": 0.04556652996689081,
"max": 0.1827950450281302,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.673748775449995e-06,
"min": 3.673748775449995e-06,
"max": 0.0002953458765513749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1021246326349985e-05,
"min": 1.1021246326349985e-05,
"max": 0.0008438751187082999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122454999999998,
"min": 0.10122454999999998,
"max": 0.19844862499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367364999999996,
"min": 0.20762374999999997,
"max": 0.5812917,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.110504499999992e-05,
"min": 7.110504499999992e-05,
"max": 0.004922586387500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021331513499999976,
"min": 0.00021331513499999976,
"max": 0.01406645583,
"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": "1678075652",
"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": "1.22.4",
"end_time_seconds": "1678078105"
},
"total": 2453.141754621,
"count": 1,
"self": 0.44053024100003313,
"children": {
"run_training.setup": {
"total": 0.1935715440000081,
"count": 1,
"self": 0.1935715440000081
},
"TrainerController.start_learning": {
"total": 2452.507652836,
"count": 1,
"self": 4.358152026898097,
"children": {
"TrainerController._reset_env": {
"total": 10.731999760999997,
"count": 1,
"self": 10.731999760999997
},
"TrainerController.advance": {
"total": 2437.3103582471026,
"count": 233263,
"self": 4.70389731520163,
"children": {
"env_step": {
"total": 1894.1923900798931,
"count": 233263,
"self": 1588.6960141327672,
"children": {
"SubprocessEnvManager._take_step": {
"total": 302.63946224908256,
"count": 233263,
"self": 16.218953641075586,
"children": {
"TorchPolicy.evaluate": {
"total": 286.42050860800697,
"count": 222948,
"self": 71.5640041240656,
"children": {
"TorchPolicy.sample_actions": {
"total": 214.85650448394136,
"count": 222948,
"self": 214.85650448394136
}
}
}
}
},
"workers": {
"total": 2.8569136980434564,
"count": 233263,
"self": 0.0,
"children": {
"worker_root": {
"total": 2444.049574331961,
"count": 233263,
"is_parallel": true,
"self": 1151.1382523080026,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012372250000112217,
"count": 1,
"is_parallel": true,
"self": 0.00047259600000870705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007646290000025147,
"count": 2,
"is_parallel": true,
"self": 0.0007646290000025147
}
}
},
"UnityEnvironment.step": {
"total": 0.028926785000010113,
"count": 1,
"is_parallel": true,
"self": 0.0003001839999683398,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001971489999732512,
"count": 1,
"is_parallel": true,
"self": 0.0001971489999732512
},
"communicator.exchange": {
"total": 0.027689375000022665,
"count": 1,
"is_parallel": true,
"self": 0.027689375000022665
},
"steps_from_proto": {
"total": 0.0007400770000458579,
"count": 1,
"is_parallel": true,
"self": 0.00025997700004154467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004801000000043132,
"count": 2,
"is_parallel": true,
"self": 0.0004801000000043132
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1292.9113220239585,
"count": 233262,
"is_parallel": true,
"self": 39.11851113088255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.79795554006006,
"count": 233262,
"is_parallel": true,
"self": 79.79795554006006
},
"communicator.exchange": {
"total": 1080.6524487009478,
"count": 233262,
"is_parallel": true,
"self": 1080.6524487009478
},
"steps_from_proto": {
"total": 93.34240665206823,
"count": 233262,
"is_parallel": true,
"self": 37.63397791910643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.708428732961806,
"count": 466524,
"is_parallel": true,
"self": 55.708428732961806
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 538.4140708520079,
"count": 233263,
"self": 6.448062147008386,
"children": {
"process_trajectory": {
"total": 170.30537531799968,
"count": 233263,
"self": 169.197588624999,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1077866930006621,
"count": 10,
"self": 1.1077866930006621
}
}
},
"_update_policy": {
"total": 361.6606333869998,
"count": 97,
"self": 303.4612271779981,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.199406209001666,
"count": 2910,
"self": 58.199406209001666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.699998943484388e-07,
"count": 1,
"self": 8.699998943484388e-07
},
"TrainerController._save_models": {
"total": 0.10714193099965996,
"count": 1,
"self": 0.002248528999643895,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10489340200001607,
"count": 1,
"self": 0.10489340200001607
}
}
}
}
}
}
}