ppo-Huggy / run_logs /timers.json
NDani's picture
Huggy
f368f1c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4049947261810303,
"min": 1.4049947261810303,
"max": 1.4285035133361816,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70645.9453125,
"min": 68491.7578125,
"max": 76840.453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.62834645669291,
"min": 67.47879616963064,
"max": 397.6587301587302,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49294.0,
"min": 49183.0,
"max": 50105.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999984.0,
"min": 49808.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999984.0,
"min": 49808.0,
"max": 1999984.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5230205059051514,
"min": -0.01708993874490261,
"max": 2.5447678565979004,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1602.1180419921875,
"min": -2.136242389678955,
"max": 1824.5986328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9293002975268627,
"min": 1.6238546508550644,
"max": 4.058913615335988,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2495.105688929558,
"min": 202.98183135688305,
"max": 2858.115658760071,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9293002975268627,
"min": 1.6238546508550644,
"max": 4.058913615335988,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2495.105688929558,
"min": 202.98183135688305,
"max": 2858.115658760071,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016573723958248996,
"min": 0.014805863444538166,
"max": 0.020329063095656845,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049721171874746985,
"min": 0.02961172688907633,
"max": 0.05753996644586247,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.055368743629919163,
"min": 0.022827326382199923,
"max": 0.06541913865755002,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16610623088975748,
"min": 0.045654652764399846,
"max": 0.18033196069300175,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.896498701199999e-06,
"min": 3.896498701199999e-06,
"max": 0.0002953305015565,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1689496103599998e-05,
"min": 1.1689496103599998e-05,
"max": 0.0008439760686746499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129880000000004,
"min": 0.10129880000000004,
"max": 0.19844349999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038964000000001,
"min": 0.20777835,
"max": 0.5813253500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.481012000000002e-05,
"min": 7.481012000000002e-05,
"max": 0.004922330650000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022443036000000004,
"min": 0.00022443036000000004,
"max": 0.014068134965,
"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": "1708352599",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708355088"
},
"total": 2489.035579687,
"count": 1,
"self": 0.4918538779993469,
"children": {
"run_training.setup": {
"total": 0.051540780000095765,
"count": 1,
"self": 0.051540780000095765
},
"TrainerController.start_learning": {
"total": 2488.492185029,
"count": 1,
"self": 4.5842605738589555,
"children": {
"TrainerController._reset_env": {
"total": 3.3394008929999472,
"count": 1,
"self": 3.3394008929999472
},
"TrainerController.advance": {
"total": 2480.428050279141,
"count": 233608,
"self": 4.89610747225197,
"children": {
"env_step": {
"total": 1975.3885890730087,
"count": 233608,
"self": 1634.847755074033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 337.5568146370749,
"count": 233608,
"self": 17.372750518062276,
"children": {
"TorchPolicy.evaluate": {
"total": 320.18406411901265,
"count": 222976,
"self": 320.18406411901265
}
}
},
"workers": {
"total": 2.984019361900664,
"count": 233608,
"self": 0.0,
"children": {
"worker_root": {
"total": 2480.987101616975,
"count": 233608,
"is_parallel": true,
"self": 1148.5588401828306,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010593990000415943,
"count": 1,
"is_parallel": true,
"self": 0.00029887800019423594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007605209998473583,
"count": 2,
"is_parallel": true,
"self": 0.0007605209998473583
}
}
},
"UnityEnvironment.step": {
"total": 0.03323599700001978,
"count": 1,
"is_parallel": true,
"self": 0.0004071299999850453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000217689999999493,
"count": 1,
"is_parallel": true,
"self": 0.000217689999999493
},
"communicator.exchange": {
"total": 0.03170164300013312,
"count": 1,
"is_parallel": true,
"self": 0.03170164300013312
},
"steps_from_proto": {
"total": 0.0009095339999021235,
"count": 1,
"is_parallel": true,
"self": 0.00023633499995412421,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006731989999479993,
"count": 2,
"is_parallel": true,
"self": 0.0006731989999479993
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1332.4282614341444,
"count": 233607,
"is_parallel": true,
"self": 43.487962740767216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.37571839520001,
"count": 233607,
"is_parallel": true,
"self": 88.37571839520001
},
"communicator.exchange": {
"total": 1104.476730389173,
"count": 233607,
"is_parallel": true,
"self": 1104.476730389173
},
"steps_from_proto": {
"total": 96.08784990900403,
"count": 233607,
"is_parallel": true,
"self": 33.60747894893393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.480370960070104,
"count": 467214,
"is_parallel": true,
"self": 62.480370960070104
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 500.14335373388053,
"count": 233608,
"self": 6.974527191769994,
"children": {
"process_trajectory": {
"total": 164.55576999411073,
"count": 233608,
"self": 163.08790912411087,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4678608699998676,
"count": 10,
"self": 1.4678608699998676
}
}
},
"_update_policy": {
"total": 328.6130565479998,
"count": 97,
"self": 263.72118614999886,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.89187039800095,
"count": 2910,
"self": 64.89187039800095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0169997040065937e-06,
"count": 1,
"self": 1.0169997040065937e-06
},
"TrainerController._save_models": {
"total": 0.1404722660004154,
"count": 1,
"self": 0.002329131000351481,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13814313500006392,
"count": 1,
"self": 0.13814313500006392
}
}
}
}
}
}
}