ppo-Huggy / run_logs /timers.json
rafay's picture
Huggy
d4f5ac6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4037513732910156,
"min": 1.4037513732910156,
"max": 1.4250457286834717,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71613.78125,
"min": 68119.1796875,
"max": 75708.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.6822033898305,
"min": 88.94802867383513,
"max": 402.71774193548384,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49410.0,
"min": 49001.0,
"max": 50147.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999504.0,
"min": 49317.0,
"max": 1999504.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999504.0,
"min": 49317.0,
"max": 1999504.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.314023733139038,
"min": -0.01856098882853985,
"max": 2.4098403453826904,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1092.21923828125,
"min": -2.283001661300659,
"max": 1333.8095703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4832116020685535,
"min": 1.7259351771052291,
"max": 3.8937651319750426,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1644.0758761763573,
"min": 212.29002678394318,
"max": 2119.184470951557,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4832116020685535,
"min": 1.7259351771052291,
"max": 3.8937651319750426,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1644.0758761763573,
"min": 212.29002678394318,
"max": 2119.184470951557,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015464123656177739,
"min": 0.0138695300094696,
"max": 0.019808846498684335,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030928247312355477,
"min": 0.0277390600189392,
"max": 0.05526747664165063,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.046367792723079525,
"min": 0.022833892796188596,
"max": 0.05954687938921982,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09273558544615905,
"min": 0.04566778559237719,
"max": 0.17864063816765946,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.6362984545999895e-06,
"min": 4.6362984545999895e-06,
"max": 0.000295316026561325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.272596909199979e-06,
"min": 9.272596909199979e-06,
"max": 0.0008439511686829499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10154540000000001,
"min": 0.10154540000000001,
"max": 0.19843867500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20309080000000002,
"min": 0.20309080000000002,
"max": 0.58131705,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.711545999999984e-05,
"min": 8.711545999999984e-05,
"max": 0.004922089882500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017423091999999968,
"min": 0.00017423091999999968,
"max": 0.014067720795000002,
"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": "1687100818",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687103194"
},
"total": 2375.74886983,
"count": 1,
"self": 0.3959660969999277,
"children": {
"run_training.setup": {
"total": 0.07427530900031343,
"count": 1,
"self": 0.07427530900031343
},
"TrainerController.start_learning": {
"total": 2375.2786284239996,
"count": 1,
"self": 4.066843991087808,
"children": {
"TrainerController._reset_env": {
"total": 4.630233524000232,
"count": 1,
"self": 4.630233524000232
},
"TrainerController.advance": {
"total": 2366.461444263912,
"count": 231583,
"self": 4.326614761936526,
"children": {
"env_step": {
"total": 1843.5770186760628,
"count": 231583,
"self": 1554.5843447654547,
"children": {
"SubprocessEnvManager._take_step": {
"total": 286.1597454507537,
"count": 231583,
"self": 16.366292413692463,
"children": {
"TorchPolicy.evaluate": {
"total": 269.7934530370612,
"count": 223054,
"self": 269.7934530370612
}
}
},
"workers": {
"total": 2.832928459854429,
"count": 231583,
"self": 0.0,
"children": {
"worker_root": {
"total": 2367.619428494966,
"count": 231583,
"is_parallel": true,
"self": 1096.3630871278874,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010544000001573295,
"count": 1,
"is_parallel": true,
"self": 0.000285907000034058,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007684930001232715,
"count": 2,
"is_parallel": true,
"self": 0.0007684930001232715
}
}
},
"UnityEnvironment.step": {
"total": 0.03151215099978799,
"count": 1,
"is_parallel": true,
"self": 0.00033919099951162934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023676699993302464,
"count": 1,
"is_parallel": true,
"self": 0.00023676699993302464
},
"communicator.exchange": {
"total": 0.03005289200018524,
"count": 1,
"is_parallel": true,
"self": 0.03005289200018524
},
"steps_from_proto": {
"total": 0.0008833010001580988,
"count": 1,
"is_parallel": true,
"self": 0.0002644989999680547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006188020001900441,
"count": 2,
"is_parallel": true,
"self": 0.0006188020001900441
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.2563413670787,
"count": 231582,
"is_parallel": true,
"self": 39.23671718708874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.68007204506557,
"count": 231582,
"is_parallel": true,
"self": 78.68007204506557
},
"communicator.exchange": {
"total": 1059.0652596788632,
"count": 231582,
"is_parallel": true,
"self": 1059.0652596788632
},
"steps_from_proto": {
"total": 94.27429245606118,
"count": 231582,
"is_parallel": true,
"self": 33.082939327173335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.19135312888784,
"count": 463164,
"is_parallel": true,
"self": 61.19135312888784
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.5578108259128,
"count": 231583,
"self": 6.457586831772915,
"children": {
"process_trajectory": {
"total": 130.19321731714308,
"count": 231583,
"self": 128.7919073921421,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4013099250009873,
"count": 10,
"self": 1.4013099250009873
}
}
},
"_update_policy": {
"total": 381.90700667699684,
"count": 96,
"self": 321.9674237420095,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.93958293498736,
"count": 2880,
"self": 59.93958293498736
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.12010570299935353,
"count": 1,
"self": 0.0019995399998151697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11810616299953836,
"count": 1,
"self": 0.11810616299953836
}
}
}
}
}
}
}