ppo-Huggy / run_logs /timers.json
dongseon's picture
Huggy
3e4e00c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070247411727905,
"min": 1.4070247411727905,
"max": 1.4284170866012573,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69471.84375,
"min": 68914.9375,
"max": 78070.2578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.02022058823529,
"min": 79.14903846153847,
"max": 420.52100840336135,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49515.0,
"min": 48969.0,
"max": 50189.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49952.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49952.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4391231536865234,
"min": -0.02040155604481697,
"max": 2.456775188446045,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1326.883056640625,
"min": -2.407383680343628,
"max": 1513.0521240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.82575778969947,
"min": 1.7553436821800168,
"max": 3.9618680324470787,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2081.212237596512,
"min": 207.13055449724197,
"max": 2378.1792350411415,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.82575778969947,
"min": 1.7553436821800168,
"max": 3.9618680324470787,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2081.212237596512,
"min": 207.13055449724197,
"max": 2378.1792350411415,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015456731637661708,
"min": 0.01335560511603641,
"max": 0.019801878435030555,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04637019491298512,
"min": 0.02671121023207282,
"max": 0.0574104313069256,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053908529422349395,
"min": 0.021889608632773158,
"max": 0.06036354497902923,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1617255882670482,
"min": 0.043779217265546316,
"max": 0.18109063493708769,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6292987902666652e-06,
"min": 3.6292987902666652e-06,
"max": 0.00029535952654682494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0887896370799996e-05,
"min": 1.0887896370799996e-05,
"max": 0.0008443066685644499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120973333333334,
"min": 0.10120973333333334,
"max": 0.198453175,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362920000000004,
"min": 0.20755255,
"max": 0.5814355500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.036569333333333e-05,
"min": 7.036569333333333e-05,
"max": 0.004922813432500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021109708,
"min": 0.00021109708,
"max": 0.014073633945000002,
"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": "1747134925",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747137473"
},
"total": 2548.0517740709997,
"count": 1,
"self": 0.6454998419999356,
"children": {
"run_training.setup": {
"total": 0.02469365599995399,
"count": 1,
"self": 0.02469365599995399
},
"TrainerController.start_learning": {
"total": 2547.381580573,
"count": 1,
"self": 4.674152648061408,
"children": {
"TrainerController._reset_env": {
"total": 3.570688206,
"count": 1,
"self": 3.570688206
},
"TrainerController.advance": {
"total": 2538.9656613159386,
"count": 232595,
"self": 4.838880415777112,
"children": {
"env_step": {
"total": 2036.9290830840077,
"count": 232595,
"self": 1604.5005132712265,
"children": {
"SubprocessEnvManager._take_step": {
"total": 429.64778858382886,
"count": 232595,
"self": 16.0616899158249,
"children": {
"TorchPolicy.evaluate": {
"total": 413.58609866800396,
"count": 222922,
"self": 413.58609866800396
}
}
},
"workers": {
"total": 2.780781228952378,
"count": 232595,
"self": 0.0,
"children": {
"worker_root": {
"total": 2540.1529449510067,
"count": 232595,
"is_parallel": true,
"self": 1228.8736115568377,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008974659999694268,
"count": 1,
"is_parallel": true,
"self": 0.00026209399993604166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006353720000333851,
"count": 2,
"is_parallel": true,
"self": 0.0006353720000333851
}
}
},
"UnityEnvironment.step": {
"total": 0.03979852200006917,
"count": 1,
"is_parallel": true,
"self": 0.0003690690000439645,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002204979999760326,
"count": 1,
"is_parallel": true,
"self": 0.0002204979999760326
},
"communicator.exchange": {
"total": 0.038483744000018305,
"count": 1,
"is_parallel": true,
"self": 0.038483744000018305
},
"steps_from_proto": {
"total": 0.0007252110000308676,
"count": 1,
"is_parallel": true,
"self": 0.00020204899999498593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005231620000358816,
"count": 2,
"is_parallel": true,
"self": 0.0005231620000358816
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.279333394169,
"count": 232594,
"is_parallel": true,
"self": 38.79595220802503,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.62418935007008,
"count": 232594,
"is_parallel": true,
"self": 83.62418935007008
},
"communicator.exchange": {
"total": 1099.2830777211184,
"count": 232594,
"is_parallel": true,
"self": 1099.2830777211184
},
"steps_from_proto": {
"total": 89.57611411495566,
"count": 232594,
"is_parallel": true,
"self": 31.536128421986632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.039985692969026,
"count": 465188,
"is_parallel": true,
"self": 58.039985692969026
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.19769781615366,
"count": 232595,
"self": 6.9856516601975045,
"children": {
"process_trajectory": {
"total": 173.03905837095772,
"count": 232595,
"self": 171.76124574895857,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2778126219991464,
"count": 10,
"self": 1.2778126219991464
}
}
},
"_update_policy": {
"total": 317.17298778499844,
"count": 97,
"self": 250.67572946599148,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.49725831900696,
"count": 2910,
"self": 66.49725831900696
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3029998626734596e-06,
"count": 1,
"self": 1.3029998626734596e-06
},
"TrainerController._save_models": {
"total": 0.1710771000002751,
"count": 1,
"self": 0.0023874060002526676,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16868969400002243,
"count": 1,
"self": 0.16868969400002243
}
}
}
}
}
}
}