ppo-Huggy / run_logs /timers.json
jbtruong's picture
Huggy
9015202
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.423305869102478,
"min": 1.4189502000808716,
"max": 1.423305869102478,
"count": 4
},
"Huggy.Policy.Entropy.sum": {
"value": 69729.1796875,
"min": 67911.6875,
"max": 78990.1171875,
"count": 4
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 225.93150684931507,
"min": 225.93150684931507,
"max": 440.00877192982455,
"count": 4
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49479.0,
"min": 49479.0,
"max": 50161.0,
"count": 4
},
"Huggy.Step.mean": {
"value": 199671.0,
"min": 49746.0,
"max": 199671.0,
"count": 4
},
"Huggy.Step.sum": {
"value": 199671.0,
"min": 49746.0,
"max": 199671.0,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7603117227554321,
"min": -0.04274524748325348,
"max": 0.7603117227554321,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 166.50827026367188,
"min": -4.8302130699157715,
"max": 166.50827026367188,
"count": 4
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.215989841173773,
"min": 1.7662392109632492,
"max": 3.215989841173773,
"count": 4
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 704.3017752170563,
"min": 199.58503083884716,
"max": 704.3017752170563,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.215989841173773,
"min": 1.7662392109632492,
"max": 3.215989841173773,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 704.3017752170563,
"min": 199.58503083884716,
"max": 704.3017752170563,
"count": 4
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015709483252915865,
"min": 0.015071525004714204,
"max": 0.01744376019341871,
"count": 4
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03141896650583173,
"min": 0.030143050009428407,
"max": 0.04670207239214505,
"count": 4
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.026268136594444512,
"min": 0.02429215625549356,
"max": 0.03194424298902353,
"count": 4
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.052536273188889024,
"min": 0.04858431251098712,
"max": 0.07594230007380248,
"count": 4
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.0002735256088247999,
"min": 0.0002735256088247999,
"max": 0.0002952946515684499,
"count": 4
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0005470512176495998,
"min": 0.0005470512176495998,
"max": 0.0008439004686998501,
"count": 4
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1911752,
"min": 0.1911752,
"max": 0.19843155,
"count": 4
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3823504,
"min": 0.3823504,
"max": 0.5813001499999999,
"count": 4
},
"Huggy.Policy.Beta.mean": {
"value": 0.004559642479999999,
"min": 0.004559642479999999,
"max": 0.004921734345,
"count": 4
},
"Huggy.Policy.Beta.sum": {
"value": 0.009119284959999998,
"min": 0.009119284959999998,
"max": 0.014066877485000004,
"count": 4
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1685114152",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685114436"
},
"total": 284.5138936809999,
"count": 1,
"self": 0.434318139999732,
"children": {
"run_training.setup": {
"total": 0.04324004400018566,
"count": 1,
"self": 0.04324004400018566
},
"TrainerController.start_learning": {
"total": 284.036335497,
"count": 1,
"self": 0.4967902000082631,
"children": {
"TrainerController._reset_env": {
"total": 4.744599276999907,
"count": 1,
"self": 4.744599276999907
},
"TrainerController.advance": {
"total": 278.79075985299187,
"count": 26821,
"self": 0.5224180660072761,
"children": {
"env_step": {
"total": 221.41470990299013,
"count": 26821,
"self": 186.43546929598074,
"children": {
"SubprocessEnvManager._take_step": {
"total": 34.6498656670135,
"count": 26821,
"self": 2.2837815259902072,
"children": {
"TorchPolicy.evaluate": {
"total": 32.36608414102329,
"count": 26404,
"self": 32.36608414102329
}
}
},
"workers": {
"total": 0.32937493999588696,
"count": 26820,
"self": 0.0,
"children": {
"worker_root": {
"total": 283.18592408397785,
"count": 26820,
"is_parallel": true,
"self": 131.4084638509678,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009731570000894862,
"count": 1,
"is_parallel": true,
"self": 0.00027761900014411367,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006955379999453726,
"count": 2,
"is_parallel": true,
"self": 0.0006955379999453726
}
}
},
"UnityEnvironment.step": {
"total": 0.058516585999996096,
"count": 1,
"is_parallel": true,
"self": 0.000346771999829798,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002427570000236301,
"count": 1,
"is_parallel": true,
"self": 0.0002427570000236301
},
"communicator.exchange": {
"total": 0.057185549999985597,
"count": 1,
"is_parallel": true,
"self": 0.057185549999985597
},
"steps_from_proto": {
"total": 0.0007415070001570712,
"count": 1,
"is_parallel": true,
"self": 0.00020626800028367143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005352389998733997,
"count": 2,
"is_parallel": true,
"self": 0.0005352389998733997
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 151.77746023301006,
"count": 26819,
"is_parallel": true,
"self": 4.574297063018776,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.023430734993099,
"count": 26819,
"is_parallel": true,
"self": 10.023430734993099
},
"communicator.exchange": {
"total": 126.09825750299183,
"count": 26819,
"is_parallel": true,
"self": 126.09825750299183
},
"steps_from_proto": {
"total": 11.081474932006358,
"count": 26819,
"is_parallel": true,
"self": 4.334015610019378,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.74745932198698,
"count": 53638,
"is_parallel": true,
"self": 6.74745932198698
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 56.85363188399447,
"count": 26820,
"self": 0.761506825000879,
"children": {
"process_trajectory": {
"total": 12.622072424993348,
"count": 26820,
"self": 12.467755984993346,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15431644000000233,
"count": 1,
"self": 0.15431644000000233
}
}
},
"_update_policy": {
"total": 43.47005263400024,
"count": 11,
"self": 36.83698045000028,
"children": {
"TorchPPOOptimizer.update": {
"total": 6.633072183999957,
"count": 330,
"self": 6.633072183999957
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3359999684325885e-06,
"count": 1,
"self": 1.3359999684325885e-06
},
"TrainerController._save_models": {
"total": 0.00418483099997502,
"count": 1,
"self": 2.472000005582231e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.004160110999919198,
"count": 1,
"self": 0.004160110999919198
}
}
}
}
}
}
}