ppo-Huggy / run_logs /timers.json
mnity's picture
Huggy
f217822
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408331274986267,
"min": 1.408331274986267,
"max": 1.4291343688964844,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71767.15625,
"min": 68365.2578125,
"max": 78992.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.65964343598056,
"min": 76.38544891640866,
"max": 428.1111111111111,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49767.0,
"min": 49201.0,
"max": 50089.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999673.0,
"min": 49562.0,
"max": 1999673.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999673.0,
"min": 49562.0,
"max": 1999673.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5016732215881348,
"min": 0.1181754544377327,
"max": 2.5016732215881348,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1543.5323486328125,
"min": 13.708353042602539,
"max": 1572.702880859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.977713028944099,
"min": 1.8802803053424275,
"max": 3.977713028944099,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2454.248938858509,
"min": 218.1125154197216,
"max": 2494.0890293717384,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.977713028944099,
"min": 1.8802803053424275,
"max": 3.977713028944099,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2454.248938858509,
"min": 218.1125154197216,
"max": 2494.0890293717384,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017533416043160187,
"min": 0.013833516073646024,
"max": 0.0220706378245571,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05260024812948056,
"min": 0.027667032147292048,
"max": 0.05796551206118844,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0597540580150154,
"min": 0.020969207336505254,
"max": 0.0597540580150154,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17926217404504619,
"min": 0.04193841467301051,
"max": 0.17926217404504619,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.770698743133323e-06,
"min": 3.770698743133323e-06,
"max": 0.000295330426556525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1312096229399968e-05,
"min": 1.1312096229399968e-05,
"max": 0.0008441164686278499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125686666666667,
"min": 0.10125686666666667,
"max": 0.1984434750000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037706,
"min": 0.20765195000000006,
"max": 0.58137215,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.271764666666652e-05,
"min": 7.271764666666652e-05,
"max": 0.0049223294025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021815293999999955,
"min": 0.00021815293999999955,
"max": 0.014070470285000001,
"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": "1696845106",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1696847724"
},
"total": 2618.100776982,
"count": 1,
"self": 0.435386489999928,
"children": {
"run_training.setup": {
"total": 0.07998353599998609,
"count": 1,
"self": 0.07998353599998609
},
"TrainerController.start_learning": {
"total": 2617.585406956,
"count": 1,
"self": 4.68872748003605,
"children": {
"TrainerController._reset_env": {
"total": 6.901466687999914,
"count": 1,
"self": 6.901466687999914
},
"TrainerController.advance": {
"total": 2605.897220143964,
"count": 233153,
"self": 5.023800699059848,
"children": {
"env_step": {
"total": 2006.5956220649805,
"count": 233153,
"self": 1656.0386268619648,
"children": {
"SubprocessEnvManager._take_step": {
"total": 347.4507831449731,
"count": 233153,
"self": 17.526177886946698,
"children": {
"TorchPolicy.evaluate": {
"total": 329.9246052580264,
"count": 222978,
"self": 329.9246052580264
}
}
},
"workers": {
"total": 3.1062120580426154,
"count": 233153,
"self": 0.0,
"children": {
"worker_root": {
"total": 2610.0291501879924,
"count": 233153,
"is_parallel": true,
"self": 1264.2873742779288,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008327460000145948,
"count": 1,
"is_parallel": true,
"self": 0.00026678900007937045,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005659569999352243,
"count": 2,
"is_parallel": true,
"self": 0.0005659569999352243
}
}
},
"UnityEnvironment.step": {
"total": 0.03455636199998935,
"count": 1,
"is_parallel": true,
"self": 0.0003354349998971884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002520470000035857,
"count": 1,
"is_parallel": true,
"self": 0.0002520470000035857
},
"communicator.exchange": {
"total": 0.033131329000070764,
"count": 1,
"is_parallel": true,
"self": 0.033131329000070764
},
"steps_from_proto": {
"total": 0.000837551000017811,
"count": 1,
"is_parallel": true,
"self": 0.0002555369999299728,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005820140000878382,
"count": 2,
"is_parallel": true,
"self": 0.0005820140000878382
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1345.7417759100636,
"count": 233152,
"is_parallel": true,
"self": 41.358230294049235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.05185794305498,
"count": 233152,
"is_parallel": true,
"self": 90.05185794305498
},
"communicator.exchange": {
"total": 1110.2357510520046,
"count": 233152,
"is_parallel": true,
"self": 1110.2357510520046
},
"steps_from_proto": {
"total": 104.09593662095472,
"count": 233152,
"is_parallel": true,
"self": 40.530787217971806,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.56514940298291,
"count": 466304,
"is_parallel": true,
"self": 63.56514940298291
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 594.277797379924,
"count": 233153,
"self": 6.644531331887606,
"children": {
"process_trajectory": {
"total": 162.3226131540381,
"count": 233153,
"self": 160.98197012503863,
"children": {
"RLTrainer._checkpoint": {
"total": 1.340643028999466,
"count": 10,
"self": 1.340643028999466
}
}
},
"_update_policy": {
"total": 425.3106528939983,
"count": 97,
"self": 362.3478077690047,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.96284512499358,
"count": 2910,
"self": 62.96284512499358
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0310000106983352e-06,
"count": 1,
"self": 1.0310000106983352e-06
},
"TrainerController._save_models": {
"total": 0.0979916129999765,
"count": 1,
"self": 0.001876042999811034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09611557000016546,
"count": 1,
"self": 0.09611557000016546
}
}
}
}
}
}
}