ppo-Huggy / run_logs /timers.json
dhajnes's picture
Huggy
88886b0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4077234268188477,
"min": 1.4077234268188477,
"max": 1.4293849468231201,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71132.265625,
"min": 68872.84375,
"max": 77161.8125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.63543788187373,
"min": 85.66840277777777,
"max": 416.74380165289256,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49412.0,
"min": 48786.0,
"max": 50426.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999407.0,
"min": 49941.0,
"max": 1999407.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999407.0,
"min": 49941.0,
"max": 1999407.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3366315364837646,
"min": 0.007806680630892515,
"max": 2.458960771560669,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1147.2861328125,
"min": 0.9368016719818115,
"max": 1380.3260498046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.678419945196319,
"min": 1.8505758700271449,
"max": 3.964917296958863,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1806.1041930913925,
"min": 222.06910440325737,
"max": 2206.2836925387383,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.678419945196319,
"min": 1.8505758700271449,
"max": 3.964917296958863,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1806.1041930913925,
"min": 222.06910440325737,
"max": 2206.2836925387383,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019728404060636723,
"min": 0.013813038254253722,
"max": 0.020006733043313338,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.039456808121273446,
"min": 0.027626076508507444,
"max": 0.05896048098784376,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05514923464506864,
"min": 0.02402579446012775,
"max": 0.05514923464506864,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11029846929013729,
"min": 0.0480515889202555,
"max": 0.15882604581614335,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5273234909249965e-06,
"min": 4.5273234909249965e-06,
"max": 0.00029532630155789996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.054646981849993e-06,
"min": 9.054646981849993e-06,
"max": 0.0008437027687657498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101509075,
"min": 0.101509075,
"max": 0.19844209999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20301815,
"min": 0.20301815,
"max": 0.58123425,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.530284249999994e-05,
"min": 8.530284249999994e-05,
"max": 0.004922260790000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001706056849999999,
"min": 0.0001706056849999999,
"max": 0.014063589075000004,
"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": "1710796676",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710799401"
},
"total": 2724.869733929,
"count": 1,
"self": 0.4436858500002927,
"children": {
"run_training.setup": {
"total": 0.06136283999990155,
"count": 1,
"self": 0.06136283999990155
},
"TrainerController.start_learning": {
"total": 2724.364685239,
"count": 1,
"self": 5.276157102007801,
"children": {
"TrainerController._reset_env": {
"total": 3.2614740320000237,
"count": 1,
"self": 3.2614740320000237
},
"TrainerController.advance": {
"total": 2715.697741233992,
"count": 231711,
"self": 5.325481494976884,
"children": {
"env_step": {
"total": 2188.1498312599515,
"count": 231711,
"self": 1806.0298645288003,
"children": {
"SubprocessEnvManager._take_step": {
"total": 378.47060869296365,
"count": 231711,
"self": 18.90814690397133,
"children": {
"TorchPolicy.evaluate": {
"total": 359.5624617889923,
"count": 222984,
"self": 359.5624617889923
}
}
},
"workers": {
"total": 3.649358038187529,
"count": 231711,
"self": 0.0,
"children": {
"worker_root": {
"total": 2715.9488363809683,
"count": 231711,
"is_parallel": true,
"self": 1264.106109004005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009851610000168876,
"count": 1,
"is_parallel": true,
"self": 0.00023438999983227404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007507710001846135,
"count": 2,
"is_parallel": true,
"self": 0.0007507710001846135
}
}
},
"UnityEnvironment.step": {
"total": 0.03388729300013438,
"count": 1,
"is_parallel": true,
"self": 0.00044263000063438085,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002334159999008989,
"count": 1,
"is_parallel": true,
"self": 0.0002334159999008989
},
"communicator.exchange": {
"total": 0.03232948099980604,
"count": 1,
"is_parallel": true,
"self": 0.03232948099980604
},
"steps_from_proto": {
"total": 0.0008817659997930605,
"count": 1,
"is_parallel": true,
"self": 0.00024107399985950906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006406919999335514,
"count": 2,
"is_parallel": true,
"self": 0.0006406919999335514
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1451.8427273769632,
"count": 231710,
"is_parallel": true,
"self": 43.82037440588101,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.27235962807708,
"count": 231710,
"is_parallel": true,
"self": 90.27235962807708
},
"communicator.exchange": {
"total": 1213.6630983929624,
"count": 231710,
"is_parallel": true,
"self": 1213.6630983929624
},
"steps_from_proto": {
"total": 104.08689495004273,
"count": 231710,
"is_parallel": true,
"self": 35.656696079967105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.43019887007563,
"count": 463420,
"is_parallel": true,
"self": 68.43019887007563
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 522.2224284790639,
"count": 231711,
"self": 8.230235356163803,
"children": {
"process_trajectory": {
"total": 166.02221283489848,
"count": 231711,
"self": 164.59086760989976,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4313452249987222,
"count": 10,
"self": 1.4313452249987222
}
}
},
"_update_policy": {
"total": 347.9699802880016,
"count": 96,
"self": 280.2816165690001,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.68836371900147,
"count": 2880,
"self": 67.68836371900147
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0920002750935964e-06,
"count": 1,
"self": 1.0920002750935964e-06
},
"TrainerController._save_models": {
"total": 0.1293117790000906,
"count": 1,
"self": 0.002222561000053247,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12708921800003736,
"count": 1,
"self": 0.12708921800003736
}
}
}
}
}
}
}