ppo-Huggy / run_logs /timers.json
Liapunov's picture
Baseline
57fe46b
raw
history blame
17.9 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052937030792236,
"min": 1.4052937030792236,
"max": 1.4274333715438843,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71432.484375,
"min": 67819.453125,
"max": 75944.390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.20454545454545,
"min": 75.35572519083969,
"max": 423.73728813559325,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49740.0,
"min": 49035.0,
"max": 50082.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999598.0,
"min": 49439.0,
"max": 1999598.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999598.0,
"min": 49439.0,
"max": 1999598.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.45591402053833,
"min": 0.06872628629207611,
"max": 2.5038020610809326,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1296.72265625,
"min": 8.040975570678711,
"max": 1580.234130859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.724997319619764,
"min": 1.7921751994862516,
"max": 4.032268193710202,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1966.7985847592354,
"min": 209.68449833989143,
"max": 2525.2176157832146,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.724997319619764,
"min": 1.7921751994862516,
"max": 4.032268193710202,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1966.7985847592354,
"min": 209.68449833989143,
"max": 2525.2176157832146,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016300647074482793,
"min": 0.013831008256723483,
"max": 0.020367371278310505,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048901941223448375,
"min": 0.027662016513446967,
"max": 0.05715179362766018,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055645398257507216,
"min": 0.021491840947419405,
"max": 0.06736401952803135,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16693619477252164,
"min": 0.04298368189483881,
"max": 0.19562530430654682,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6597487801166697e-06,
"min": 3.6597487801166697e-06,
"max": 0.00029530132656622495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0979246340350009e-05,
"min": 1.0979246340350009e-05,
"max": 0.00084394396868535,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121988333333336,
"min": 0.10121988333333336,
"max": 0.19843377500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365965000000006,
"min": 0.20760119999999999,
"max": 0.5813146499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.087217833333339e-05,
"min": 7.087217833333339e-05,
"max": 0.0049218453725,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021261653500000016,
"min": 0.00021261653500000016,
"max": 0.014067601034999998,
"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": "1671012132",
"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": "1671016448"
},
"total": 4315.8683782630005,
"count": 1,
"self": 0.5473664740002278,
"children": {
"run_training.setup": {
"total": 0.14487471600023127,
"count": 1,
"self": 0.14487471600023127
},
"TrainerController.start_learning": {
"total": 4315.176137073,
"count": 1,
"self": 7.493781952804966,
"children": {
"TrainerController._reset_env": {
"total": 10.953159468000194,
"count": 1,
"self": 10.953159468000194
},
"TrainerController.advance": {
"total": 4296.566211426194,
"count": 232673,
"self": 7.179787847677289,
"children": {
"env_step": {
"total": 2772.421115996626,
"count": 232673,
"self": 2368.422044177617,
"children": {
"SubprocessEnvManager._take_step": {
"total": 398.68985272726604,
"count": 232673,
"self": 26.67514966957515,
"children": {
"TorchPolicy.evaluate": {
"total": 372.0147030576909,
"count": 222981,
"self": 56.59739645037462,
"children": {
"TorchPolicy.sample_actions": {
"total": 315.4173066073163,
"count": 222981,
"self": 315.4173066073163
}
}
}
}
},
"workers": {
"total": 5.309219091743216,
"count": 232673,
"self": 0.0,
"children": {
"worker_root": {
"total": 4299.269519961151,
"count": 232673,
"is_parallel": true,
"self": 2381.5261077731147,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007259042999976373,
"count": 1,
"is_parallel": true,
"self": 0.0005335949999789591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006725447999997414,
"count": 2,
"is_parallel": true,
"self": 0.006725447999997414
}
}
},
"UnityEnvironment.step": {
"total": 0.03724455300016416,
"count": 1,
"is_parallel": true,
"self": 0.00033946500025194837,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022646500019618543,
"count": 1,
"is_parallel": true,
"self": 0.00022646500019618543
},
"communicator.exchange": {
"total": 0.03566169399982755,
"count": 1,
"is_parallel": true,
"self": 0.03566169399982755
},
"steps_from_proto": {
"total": 0.0010169289998884778,
"count": 1,
"is_parallel": true,
"self": 0.00029216300026746467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007247659996210132,
"count": 2,
"is_parallel": true,
"self": 0.0007247659996210132
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1917.743412188036,
"count": 232672,
"is_parallel": true,
"self": 56.69368117062368,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.77090700612916,
"count": 232672,
"is_parallel": true,
"self": 84.77090700612916
},
"communicator.exchange": {
"total": 1631.2352220198309,
"count": 232672,
"is_parallel": true,
"self": 1631.2352220198309
},
"steps_from_proto": {
"total": 145.0436019914523,
"count": 232672,
"is_parallel": true,
"self": 55.63765301290459,
"children": {
"_process_rank_one_or_two_observation": {
"total": 89.40594897854771,
"count": 465344,
"is_parallel": true,
"self": 89.40594897854771
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1516.9653075818906,
"count": 232673,
"self": 11.453820901794643,
"children": {
"process_trajectory": {
"total": 241.5448609940995,
"count": 232673,
"self": 240.97262066709845,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5722403270010545,
"count": 4,
"self": 0.5722403270010545
}
}
},
"_update_policy": {
"total": 1263.9666256859964,
"count": 97,
"self": 321.90236154803733,
"children": {
"TorchPPOOptimizer.update": {
"total": 942.0642641379591,
"count": 2910,
"self": 942.0642641379591
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.679999154992402e-07,
"count": 1,
"self": 8.679999154992402e-07
},
"TrainerController._save_models": {
"total": 0.162983358000929,
"count": 1,
"self": 0.005531131999305217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15745222600162379,
"count": 1,
"self": 0.15745222600162379
}
}
}
}
}
}
}