ppo-Huggy / run_logs /timers.json
ValentinGuigon's picture
Huggy
5e2ec43 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4096527099609375,
"min": 1.4096527099609375,
"max": 1.4303053617477417,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70510.828125,
"min": 68369.953125,
"max": 77244.71875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.84496124031008,
"min": 87.08802816901408,
"max": 410.8114754098361,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49456.0,
"min": 48751.0,
"max": 50181.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999927.0,
"min": 49841.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999927.0,
"min": 49841.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3247058391571045,
"min": 0.12000440061092377,
"max": 2.44474458694458,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1199.5482177734375,
"min": 14.520532608032227,
"max": 1354.2156982421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.621741550375325,
"min": 1.911548749967055,
"max": 3.8815487810345584,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1868.8186399936676,
"min": 231.29739874601364,
"max": 2154.50323843956,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.621741550375325,
"min": 1.911548749967055,
"max": 3.8815487810345584,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1868.8186399936676,
"min": 231.29739874601364,
"max": 2154.50323843956,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013423316472737512,
"min": 0.013423316472737512,
"max": 0.020815561865068354,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04026994941821253,
"min": 0.027335251465653226,
"max": 0.05918704193706314,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057673347410228525,
"min": 0.02210447530572613,
"max": 0.05935502536594867,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17302004223068557,
"min": 0.04420895061145226,
"max": 0.17806507609784603,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.490598836499997e-06,
"min": 3.490598836499997e-06,
"max": 0.000295371376542875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.047179650949999e-05,
"min": 1.047179650949999e-05,
"max": 0.0008440978686340498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116349999999998,
"min": 0.10116349999999998,
"max": 0.198457125,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30349049999999994,
"min": 0.20747665000000004,
"max": 0.5813659499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.805864999999996e-05,
"min": 6.805864999999996e-05,
"max": 0.004923010537500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020417594999999988,
"min": 0.00020417594999999988,
"max": 0.014070160904999999,
"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": "1720309770",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720315143"
},
"total": 5373.846229418,
"count": 1,
"self": 0.597272564999912,
"children": {
"run_training.setup": {
"total": 0.08057314400002724,
"count": 1,
"self": 0.08057314400002724
},
"TrainerController.start_learning": {
"total": 5373.1683837089995,
"count": 1,
"self": 9.818099831206382,
"children": {
"TrainerController._reset_env": {
"total": 3.6013831750000236,
"count": 1,
"self": 3.6013831750000236
},
"TrainerController.advance": {
"total": 5359.6314484457935,
"count": 232108,
"self": 9.778843969813352,
"children": {
"env_step": {
"total": 3475.240964988092,
"count": 232108,
"self": 2890.443276457138,
"children": {
"SubprocessEnvManager._take_step": {
"total": 578.2693419618784,
"count": 232108,
"self": 35.281115255003215,
"children": {
"TorchPolicy.evaluate": {
"total": 542.9882267068751,
"count": 222991,
"self": 542.9882267068751
}
}
},
"workers": {
"total": 6.528346569075552,
"count": 232108,
"self": 0.0,
"children": {
"worker_root": {
"total": 5357.6590307500755,
"count": 232108,
"is_parallel": true,
"self": 3071.835361105213,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001611205000017435,
"count": 1,
"is_parallel": true,
"self": 0.00041050299989819905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012007020001192359,
"count": 2,
"is_parallel": true,
"self": 0.0012007020001192359
}
}
},
"UnityEnvironment.step": {
"total": 0.04582959499998651,
"count": 1,
"is_parallel": true,
"self": 0.0005175870001039584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032412099994871824,
"count": 1,
"is_parallel": true,
"self": 0.00032412099994871824
},
"communicator.exchange": {
"total": 0.04398492500001794,
"count": 1,
"is_parallel": true,
"self": 0.04398492500001794
},
"steps_from_proto": {
"total": 0.0010029619999158967,
"count": 1,
"is_parallel": true,
"self": 0.00025811399996200635,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007448479999538904,
"count": 2,
"is_parallel": true,
"self": 0.0007448479999538904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2285.8236696448625,
"count": 232107,
"is_parallel": true,
"self": 70.89888421002524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 118.51366815088488,
"count": 232107,
"is_parallel": true,
"self": 118.51366815088488
},
"communicator.exchange": {
"total": 1942.7184701170586,
"count": 232107,
"is_parallel": true,
"self": 1942.7184701170586
},
"steps_from_proto": {
"total": 153.69264716689406,
"count": 232107,
"is_parallel": true,
"self": 49.394392400939864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 104.2982547659542,
"count": 464214,
"is_parallel": true,
"self": 104.2982547659542
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1874.6116394878877,
"count": 232108,
"self": 16.89656323984991,
"children": {
"process_trajectory": {
"total": 290.90522290803983,
"count": 232108,
"self": 289.4104725400384,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4947503680014051,
"count": 10,
"self": 1.4947503680014051
}
}
},
"_update_policy": {
"total": 1566.809853339998,
"count": 97,
"self": 372.23912514200424,
"children": {
"TorchPPOOptimizer.update": {
"total": 1194.5707281979937,
"count": 2910,
"self": 1194.5707281979937
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2860000424552709e-06,
"count": 1,
"self": 1.2860000424552709e-06
},
"TrainerController._save_models": {
"total": 0.11745097099992563,
"count": 1,
"self": 0.00305560200013133,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1143953689997943,
"count": 1,
"self": 0.1143953689997943
}
}
}
}
}
}
}