ppo-huggy / run_logs /timers.json
UXAIR's picture
Huggy
934235c verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4080619812011719,
"min": 1.4080619812011719,
"max": 1.4294006824493408,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69725.8203125,
"min": 67821.703125,
"max": 76443.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 124.87405541561712,
"min": 101.81687242798354,
"max": 429.77777777777777,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49575.0,
"min": 48948.0,
"max": 50284.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49918.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49918.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3205032348632812,
"min": -0.03601861000061035,
"max": 2.3647897243499756,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 921.23974609375,
"min": -4.178158760070801,
"max": 1149.287841796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.553906972972812,
"min": 1.6019266031939408,
"max": 3.8551501782847124,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1410.9010682702065,
"min": 185.82348597049713,
"max": 1863.4155290722847,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.553906972972812,
"min": 1.6019266031939408,
"max": 3.8551501782847124,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1410.9010682702065,
"min": 185.82348597049713,
"max": 1863.4155290722847,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01658295805633922,
"min": 0.013939697050955147,
"max": 0.02032732452401736,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03316591611267844,
"min": 0.027879394101910294,
"max": 0.05558358233247418,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04322298007706801,
"min": 0.023794898111373183,
"max": 0.06415957870582739,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08644596015413603,
"min": 0.04758979622274637,
"max": 0.19121651525298752,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.320248559949995e-06,
"min": 4.320248559949995e-06,
"max": 0.0002953569015477,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.64049711989999e-06,
"min": 8.64049711989999e-06,
"max": 0.00084413416862195,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10144004999999998,
"min": 0.10144004999999998,
"max": 0.1984523,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20288009999999995,
"min": 0.20288009999999995,
"max": 0.5813780500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.185849499999992e-05,
"min": 8.185849499999992e-05,
"max": 0.00492276977,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016371698999999984,
"min": 0.00016371698999999984,
"max": 0.014070764694999998,
"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": "1713351465",
"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": "1713353841"
},
"total": 2375.3972490789997,
"count": 1,
"self": 0.44094533199995567,
"children": {
"run_training.setup": {
"total": 0.08763898699999118,
"count": 1,
"self": 0.08763898699999118
},
"TrainerController.start_learning": {
"total": 2374.86866476,
"count": 1,
"self": 4.155760409972572,
"children": {
"TrainerController._reset_env": {
"total": 3.0861743039999965,
"count": 1,
"self": 3.0861743039999965
},
"TrainerController.advance": {
"total": 2367.512676995027,
"count": 230602,
"self": 4.4604915238969625,
"children": {
"env_step": {
"total": 1880.833253382035,
"count": 230602,
"self": 1558.8685244729963,
"children": {
"SubprocessEnvManager._take_step": {
"total": 319.26000730703163,
"count": 230602,
"self": 18.51985959800163,
"children": {
"TorchPolicy.evaluate": {
"total": 300.74014770903,
"count": 222932,
"self": 300.74014770903
}
}
},
"workers": {
"total": 2.704721602007112,
"count": 230602,
"self": 0.0,
"children": {
"worker_root": {
"total": 2368.0055312711197,
"count": 230602,
"is_parallel": true,
"self": 1107.136057232134,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008894549998785806,
"count": 1,
"is_parallel": true,
"self": 0.00021420199959720776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006752530002813728,
"count": 2,
"is_parallel": true,
"self": 0.0006752530002813728
}
}
},
"UnityEnvironment.step": {
"total": 0.029018838000183678,
"count": 1,
"is_parallel": true,
"self": 0.000374964000457112,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020557099992402073,
"count": 1,
"is_parallel": true,
"self": 0.00020557099992402073
},
"communicator.exchange": {
"total": 0.027689401999850816,
"count": 1,
"is_parallel": true,
"self": 0.027689401999850816
},
"steps_from_proto": {
"total": 0.0007489009999517293,
"count": 1,
"is_parallel": true,
"self": 0.00018655999997463368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005623409999770956,
"count": 2,
"is_parallel": true,
"self": 0.0005623409999770956
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.8694740389858,
"count": 230601,
"is_parallel": true,
"self": 39.2231520870057,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.75748257205464,
"count": 230601,
"is_parallel": true,
"self": 82.75748257205464
},
"communicator.exchange": {
"total": 1047.527587768995,
"count": 230601,
"is_parallel": true,
"self": 1047.527587768995
},
"steps_from_proto": {
"total": 91.36125161093037,
"count": 230601,
"is_parallel": true,
"self": 32.55594967597949,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.805301934950876,
"count": 461202,
"is_parallel": true,
"self": 58.805301934950876
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.218932089095,
"count": 230602,
"self": 6.381125314316023,
"children": {
"process_trajectory": {
"total": 139.37567257777846,
"count": 230602,
"self": 138.04342923077888,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3322433469995758,
"count": 10,
"self": 1.3322433469995758
}
}
},
"_update_policy": {
"total": 336.4621341970005,
"count": 96,
"self": 272.3833732150015,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.07876098199904,
"count": 2880,
"self": 64.07876098199904
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4170000213198364e-06,
"count": 1,
"self": 1.4170000213198364e-06
},
"TrainerController._save_models": {
"total": 0.11405163400013407,
"count": 1,
"self": 0.0018661149997569737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1121855190003771,
"count": 1,
"self": 0.1121855190003771
}
}
}
}
}
}
}