ppo-Huggy / run_logs /timers.json
timflash's picture
Huggy
5e3f70f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3974882364273071,
"min": 1.3974882364273071,
"max": 1.4268425703048706,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71654.8125,
"min": 67834.9453125,
"max": 78355.6328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.67234042553191,
"min": 87.49557522123894,
"max": 399.75396825396825,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49666.0,
"min": 48957.0,
"max": 50369.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49948.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49948.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.390542984008789,
"min": 0.0729413777589798,
"max": 2.4135594367980957,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1121.1646728515625,
"min": 9.117671966552734,
"max": 1297.99609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.597892391402076,
"min": 1.8088119938373566,
"max": 3.8554002376562657,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1687.4115315675735,
"min": 226.10149922966957,
"max": 2014.6686896681786,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.597892391402076,
"min": 1.8088119938373566,
"max": 3.8554002376562657,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1687.4115315675735,
"min": 226.10149922966957,
"max": 2014.6686896681786,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013596693124175848,
"min": 0.013455480233324124,
"max": 0.019574986250760654,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04079007937252754,
"min": 0.02691096046664825,
"max": 0.056554807187058034,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.042293218336999415,
"min": 0.021634186897426844,
"max": 0.05744205024093389,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12687965501099824,
"min": 0.04326837379485369,
"max": 0.16615669205784797,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3372988876000065e-06,
"min": 3.3372988876000065e-06,
"max": 0.000295342276552575,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0011896662800019e-05,
"min": 1.0011896662800019e-05,
"max": 0.0008442595685801501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10111239999999999,
"min": 0.10111239999999999,
"max": 0.198447425,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033372,
"min": 0.20738945,
"max": 0.5814198499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.550876000000012e-05,
"min": 6.550876000000012e-05,
"max": 0.004922526507500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019652628000000035,
"min": 0.00019652628000000035,
"max": 0.014072850514999999,
"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": "1757214669",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757217075"
},
"total": 2406.016286956,
"count": 1,
"self": 0.4479832990000432,
"children": {
"run_training.setup": {
"total": 0.025115650000088863,
"count": 1,
"self": 0.025115650000088863
},
"TrainerController.start_learning": {
"total": 2405.543188007,
"count": 1,
"self": 3.994158889007849,
"children": {
"TrainerController._reset_env": {
"total": 2.8347592000000077,
"count": 1,
"self": 2.8347592000000077
},
"TrainerController.advance": {
"total": 2398.6143847009926,
"count": 231516,
"self": 4.183699819164303,
"children": {
"env_step": {
"total": 1922.0354912388577,
"count": 231516,
"self": 1526.364308504624,
"children": {
"SubprocessEnvManager._take_step": {
"total": 393.0676960321864,
"count": 231516,
"self": 15.081261630886502,
"children": {
"TorchPolicy.evaluate": {
"total": 377.9864344012999,
"count": 223064,
"self": 377.9864344012999
}
}
},
"workers": {
"total": 2.6034867020473484,
"count": 231516,
"self": 0.0,
"children": {
"worker_root": {
"total": 2398.227426141066,
"count": 231516,
"is_parallel": true,
"self": 1152.2287174782036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009109090001402365,
"count": 1,
"is_parallel": true,
"self": 0.00037742800009255006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005334810000476864,
"count": 2,
"is_parallel": true,
"self": 0.0005334810000476864
}
}
},
"UnityEnvironment.step": {
"total": 0.030450312000084523,
"count": 1,
"is_parallel": true,
"self": 0.0003434260004269163,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001970599998912803,
"count": 1,
"is_parallel": true,
"self": 0.0001970599998912803
},
"communicator.exchange": {
"total": 0.029171625999879325,
"count": 1,
"is_parallel": true,
"self": 0.029171625999879325
},
"steps_from_proto": {
"total": 0.0007381999998870015,
"count": 1,
"is_parallel": true,
"self": 0.00023935499984872877,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004988450000382727,
"count": 2,
"is_parallel": true,
"self": 0.0004988450000382727
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.9987086628626,
"count": 231515,
"is_parallel": true,
"self": 37.15769862676552,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.07213287414424,
"count": 231515,
"is_parallel": true,
"self": 83.07213287414424
},
"communicator.exchange": {
"total": 1037.9300025369355,
"count": 231515,
"is_parallel": true,
"self": 1037.9300025369355
},
"steps_from_proto": {
"total": 87.8388746250173,
"count": 231515,
"is_parallel": true,
"self": 32.86847890675199,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.97039571826531,
"count": 463030,
"is_parallel": true,
"self": 54.97039571826531
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.3951936429705,
"count": 231516,
"self": 6.231451931062793,
"children": {
"process_trajectory": {
"total": 146.16054670790504,
"count": 231516,
"self": 144.89487357690564,
"children": {
"RLTrainer._checkpoint": {
"total": 1.265673130999403,
"count": 10,
"self": 1.265673130999403
}
}
},
"_update_policy": {
"total": 320.0031950040027,
"count": 97,
"self": 257.1107748300183,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.89242017398442,
"count": 2910,
"self": 62.89242017398442
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0049998309114017e-06,
"count": 1,
"self": 1.0049998309114017e-06
},
"TrainerController._save_models": {
"total": 0.09988421199977893,
"count": 1,
"self": 0.001570123999954376,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09831408799982455,
"count": 1,
"self": 0.09831408799982455
}
}
}
}
}
}
}