ppo-Huggy / run_logs /timers.json
TootToot's picture
Huggy
b170c42
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403124451637268,
"min": 1.403124451637268,
"max": 1.4271317720413208,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70533.6640625,
"min": 68424.6484375,
"max": 77078.6953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.58377425044091,
"min": 76.67554858934169,
"max": 387.94573643410854,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49093.0,
"min": 48919.0,
"max": 50141.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999930.0,
"min": 49738.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999930.0,
"min": 49738.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4486279487609863,
"min": 0.07911801338195801,
"max": 2.50622296333313,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1388.3720703125,
"min": 10.127105712890625,
"max": 1549.3192138671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8139860671033303,
"min": 1.795990341110155,
"max": 3.985260358931106,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2162.5301000475883,
"min": 229.88676366209984,
"max": 2452.622166156769,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8139860671033303,
"min": 1.795990341110155,
"max": 3.985260358931106,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2162.5301000475883,
"min": 229.88676366209984,
"max": 2452.622166156769,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.020092773633142418,
"min": 0.012592659465735779,
"max": 0.020587260076717937,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06027832089942725,
"min": 0.025185318931471558,
"max": 0.061761780230153815,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06541144243545002,
"min": 0.023115050295988718,
"max": 0.0654540087406834,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19623432730635007,
"min": 0.046230100591977435,
"max": 0.19623432730635007,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6101987966333274e-06,
"min": 3.6101987966333274e-06,
"max": 0.000295346026551325,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0830596389899982e-05,
"min": 1.0830596389899982e-05,
"max": 0.0008440482186505998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120336666666664,
"min": 0.10120336666666664,
"max": 0.19844867499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361009999999994,
"min": 0.20756005,
"max": 0.5813493999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.004799666666658e-05,
"min": 7.004799666666658e-05,
"max": 0.0049225888825000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021014398999999977,
"min": 0.00021014398999999977,
"max": 0.014069335059999997,
"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": "1683819497",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683821844"
},
"total": 2346.97648214,
"count": 1,
"self": 0.43777926000029765,
"children": {
"run_training.setup": {
"total": 0.06755743899998379,
"count": 1,
"self": 0.06755743899998379
},
"TrainerController.start_learning": {
"total": 2346.471145441,
"count": 1,
"self": 4.112770355036901,
"children": {
"TrainerController._reset_env": {
"total": 4.468887656000106,
"count": 1,
"self": 4.468887656000106
},
"TrainerController.advance": {
"total": 2337.7474697519633,
"count": 232893,
"self": 4.29859309899939,
"children": {
"env_step": {
"total": 1815.0060323550993,
"count": 232893,
"self": 1535.6669886021568,
"children": {
"SubprocessEnvManager._take_step": {
"total": 276.6194126289438,
"count": 232893,
"self": 16.138814581058455,
"children": {
"TorchPolicy.evaluate": {
"total": 260.48059804788534,
"count": 222960,
"self": 260.48059804788534
}
}
},
"workers": {
"total": 2.7196311239985107,
"count": 232893,
"self": 0.0,
"children": {
"worker_root": {
"total": 2338.7060938279888,
"count": 232893,
"is_parallel": true,
"self": 1081.6073131250346,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012246179999237938,
"count": 1,
"is_parallel": true,
"self": 0.0003168209999557803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009077969999680136,
"count": 2,
"is_parallel": true,
"self": 0.0009077969999680136
}
}
},
"UnityEnvironment.step": {
"total": 0.02829281199990419,
"count": 1,
"is_parallel": true,
"self": 0.00031350799997653667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000174994999952105,
"count": 1,
"is_parallel": true,
"self": 0.000174994999952105
},
"communicator.exchange": {
"total": 0.027110171999993327,
"count": 1,
"is_parallel": true,
"self": 0.027110171999993327
},
"steps_from_proto": {
"total": 0.00069413699998222,
"count": 1,
"is_parallel": true,
"self": 0.00021510900000976108,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047902799997245893,
"count": 2,
"is_parallel": true,
"self": 0.00047902799997245893
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1257.0987807029542,
"count": 232892,
"is_parallel": true,
"self": 38.27769059905904,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.01381891188248,
"count": 232892,
"is_parallel": true,
"self": 77.01381891188248
},
"communicator.exchange": {
"total": 1050.2927384460377,
"count": 232892,
"is_parallel": true,
"self": 1050.2927384460377
},
"steps_from_proto": {
"total": 91.51453274597498,
"count": 232892,
"is_parallel": true,
"self": 33.91195356080425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.602579185170725,
"count": 465784,
"is_parallel": true,
"self": 57.602579185170725
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 518.4428442978646,
"count": 232893,
"self": 6.360000005963343,
"children": {
"process_trajectory": {
"total": 132.92127038290084,
"count": 232893,
"self": 131.50784617590114,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4134242069997072,
"count": 10,
"self": 1.4134242069997072
}
}
},
"_update_policy": {
"total": 379.16157390900037,
"count": 97,
"self": 319.6634817490009,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.49809215999949,
"count": 2910,
"self": 59.49809215999949
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3270000636111945e-06,
"count": 1,
"self": 1.3270000636111945e-06
},
"TrainerController._save_models": {
"total": 0.142016350999711,
"count": 1,
"self": 0.002214623999861942,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13980172699984905,
"count": 1,
"self": 0.13980172699984905
}
}
}
}
}
}
}