ppo-Huggy / run_logs /timers.json
jake-snake's picture
Huggy
a4a4590 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404119610786438,
"min": 1.4041067361831665,
"max": 1.428821086883545,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72129.625,
"min": 68823.7578125,
"max": 77221.609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.84105960264901,
"min": 78.82165605095541,
"max": 417.801652892562,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49432.0,
"min": 48864.0,
"max": 50554.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999995.0,
"min": 49965.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999995.0,
"min": 49965.0,
"max": 1999995.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.460538864135742,
"min": 0.0477389357984066,
"max": 2.5439469814300537,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1486.1654052734375,
"min": 5.728672504425049,
"max": 1560.131591796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.772870453284276,
"min": 1.8656351720293363,
"max": 3.992286440404697,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2278.813753783703,
"min": 223.87622064352036,
"max": 2428.375701367855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.772870453284276,
"min": 1.8656351720293363,
"max": 3.992286440404697,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2278.813753783703,
"min": 223.87622064352036,
"max": 2428.375701367855,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01765960829975989,
"min": 0.013934223456372921,
"max": 0.019621275339644247,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05297882489927967,
"min": 0.02844882884140437,
"max": 0.05688707002166969,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05828218675322003,
"min": 0.024854145757853986,
"max": 0.06130261899282535,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17484656025966008,
"min": 0.04997718588759502,
"max": 0.17484656025966008,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5104988298666697e-06,
"min": 3.5104988298666697e-06,
"max": 0.0002952808515730499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0531496489600009e-05,
"min": 1.0531496489600009e-05,
"max": 0.0008440635186454999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117013333333334,
"min": 0.10117013333333334,
"max": 0.19842695,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035104,
"min": 0.20748685,
"max": 0.5813545000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.838965333333337e-05,
"min": 6.838965333333337e-05,
"max": 0.004921504804999998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002051689600000001,
"min": 0.0002051689600000001,
"max": 0.01406958955,
"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": "1760450173",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760452874"
},
"total": 2700.570087447,
"count": 1,
"self": 0.43393880700023146,
"children": {
"run_training.setup": {
"total": 0.030168591999995442,
"count": 1,
"self": 0.030168591999995442
},
"TrainerController.start_learning": {
"total": 2700.1059800479998,
"count": 1,
"self": 4.858901576853896,
"children": {
"TrainerController._reset_env": {
"total": 3.222145349000016,
"count": 1,
"self": 3.222145349000016
},
"TrainerController.advance": {
"total": 2691.926158326146,
"count": 233177,
"self": 4.724691637037267,
"children": {
"env_step": {
"total": 2211.392090211042,
"count": 233177,
"self": 1790.0619295540396,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.43601344191984,
"count": 233177,
"self": 16.185568079009045,
"children": {
"TorchPolicy.evaluate": {
"total": 402.2504453629108,
"count": 223100,
"self": 402.2504453629108
}
}
},
"workers": {
"total": 2.894147215082853,
"count": 233177,
"self": 0.0,
"children": {
"worker_root": {
"total": 2686.76533125301,
"count": 233177,
"is_parallel": true,
"self": 1235.7827855979178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008968029999323335,
"count": 1,
"is_parallel": true,
"self": 0.00025891199982197577,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006378910001103577,
"count": 2,
"is_parallel": true,
"self": 0.0006378910001103577
}
}
},
"UnityEnvironment.step": {
"total": 0.049600488000010046,
"count": 1,
"is_parallel": true,
"self": 0.00029338299998471484,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020064700004240876,
"count": 1,
"is_parallel": true,
"self": 0.00020064700004240876
},
"communicator.exchange": {
"total": 0.04838060800000221,
"count": 1,
"is_parallel": true,
"self": 0.04838060800000221
},
"steps_from_proto": {
"total": 0.00072584999998071,
"count": 1,
"is_parallel": true,
"self": 0.00018742300005669676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005384269999240132,
"count": 2,
"is_parallel": true,
"self": 0.0005384269999240132
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1450.9825456550923,
"count": 233176,
"is_parallel": true,
"self": 39.216696481140616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.67487843702838,
"count": 233176,
"is_parallel": true,
"self": 86.67487843702838
},
"communicator.exchange": {
"total": 1229.5730006289687,
"count": 233176,
"is_parallel": true,
"self": 1229.5730006289687
},
"steps_from_proto": {
"total": 95.51797010795462,
"count": 233176,
"is_parallel": true,
"self": 34.21905885602439,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.298911251930235,
"count": 466352,
"is_parallel": true,
"self": 61.298911251930235
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 475.8093764780666,
"count": 233177,
"self": 7.373313065972297,
"children": {
"process_trajectory": {
"total": 165.11155889109784,
"count": 233177,
"self": 164.01353833409883,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0980205569990176,
"count": 10,
"self": 1.0980205569990176
}
}
},
"_update_policy": {
"total": 303.32450452099647,
"count": 97,
"self": 240.358840267,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.965664253996465,
"count": 2910,
"self": 62.965664253996465
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.889996934158262e-07,
"count": 1,
"self": 8.889996934158262e-07
},
"TrainerController._save_models": {
"total": 0.09877390700012256,
"count": 1,
"self": 0.0013066520004940685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0974672549996285,
"count": 1,
"self": 0.0974672549996285
}
}
}
}
}
}
}