bonus_unit1_RL / run_logs /timers.json
yonghonglin's picture
Huggy
f40728d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4076429605484009,
"min": 1.4076429605484009,
"max": 1.4284634590148926,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69261.6640625,
"min": 68246.46875,
"max": 77264.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.7483660130719,
"min": 76.56589147286822,
"max": 396.23809523809524,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49418.0,
"min": 48966.0,
"max": 50052.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999986.0,
"min": 49990.0,
"max": 1999986.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999986.0,
"min": 49990.0,
"max": 1999986.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.429237127304077,
"min": 0.16187065839767456,
"max": 2.503669500350952,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1486.693115234375,
"min": 20.23383140563965,
"max": 1575.009765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.687639981995221,
"min": 1.9118744304180146,
"max": 4.007058409630945,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2256.8356689810753,
"min": 238.98430380225182,
"max": 2515.6708344221115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.687639981995221,
"min": 1.9118744304180146,
"max": 4.007058409630945,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2256.8356689810753,
"min": 238.98430380225182,
"max": 2515.6708344221115,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016027745086466892,
"min": 0.013340124126019268,
"max": 0.02071659924258711,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.048083235259400676,
"min": 0.027456766310691213,
"max": 0.058193265314912423,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05499686242805587,
"min": 0.02154389691228668,
"max": 0.06307990141212941,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1649905872841676,
"min": 0.04308779382457336,
"max": 0.17475872946282228,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4935988355000052e-06,
"min": 3.4935988355000052e-06,
"max": 0.00029527522657492495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0480796506500016e-05,
"min": 1.0480796506500016e-05,
"max": 0.0008439777186740999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011645,
"min": 0.1011645,
"max": 0.19842507499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034935,
"min": 0.2074666,
"max": 0.5813259000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.810855000000011e-05,
"min": 6.810855000000011e-05,
"max": 0.0049214112425,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020432565000000032,
"min": 0.00020432565000000032,
"max": 0.014068162410000001,
"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": "1740490198",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740492577"
},
"total": 2379.022724451,
"count": 1,
"self": 0.7486680980000529,
"children": {
"run_training.setup": {
"total": 0.023053603999983352,
"count": 1,
"self": 0.023053603999983352
},
"TrainerController.start_learning": {
"total": 2378.2510027490002,
"count": 1,
"self": 4.176682408049601,
"children": {
"TrainerController._reset_env": {
"total": 3.0870818160000226,
"count": 1,
"self": 3.0870818160000226
},
"TrainerController.advance": {
"total": 2370.81755581495,
"count": 233012,
"self": 4.392968953998206,
"children": {
"env_step": {
"total": 1880.8124912499372,
"count": 233012,
"self": 1472.598158736197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 405.657113017877,
"count": 233012,
"self": 15.129473498919424,
"children": {
"TorchPolicy.evaluate": {
"total": 390.5276395189576,
"count": 222971,
"self": 390.5276395189576
}
}
},
"workers": {
"total": 2.557219495863137,
"count": 233012,
"self": 0.0,
"children": {
"worker_root": {
"total": 2371.1129251929883,
"count": 233012,
"is_parallel": true,
"self": 1168.484695453045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010716259999981048,
"count": 1,
"is_parallel": true,
"self": 0.0003970570001001761,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006745689998979287,
"count": 2,
"is_parallel": true,
"self": 0.0006745689998979287
}
}
},
"UnityEnvironment.step": {
"total": 0.028263853999987987,
"count": 1,
"is_parallel": true,
"self": 0.0003042670000468206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019027200005439227,
"count": 1,
"is_parallel": true,
"self": 0.00019027200005439227
},
"communicator.exchange": {
"total": 0.027064637999956176,
"count": 1,
"is_parallel": true,
"self": 0.027064637999956176
},
"steps_from_proto": {
"total": 0.000704676999930598,
"count": 1,
"is_parallel": true,
"self": 0.00019971199992596667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005049650000046313,
"count": 2,
"is_parallel": true,
"self": 0.0005049650000046313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1202.6282297399432,
"count": 233011,
"is_parallel": true,
"self": 36.78630408702634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.58171118709402,
"count": 233011,
"is_parallel": true,
"self": 78.58171118709402
},
"communicator.exchange": {
"total": 1002.6294640559348,
"count": 233011,
"is_parallel": true,
"self": 1002.6294640559348
},
"steps_from_proto": {
"total": 84.63075040988804,
"count": 233011,
"is_parallel": true,
"self": 29.842755879881338,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.7879945300067,
"count": 466022,
"is_parallel": true,
"self": 54.7879945300067
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 485.6120956110145,
"count": 233012,
"self": 6.247446625048724,
"children": {
"process_trajectory": {
"total": 159.7721560349654,
"count": 233012,
"self": 158.38853329696497,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3836227380004402,
"count": 10,
"self": 1.3836227380004402
}
}
},
"_update_policy": {
"total": 319.5924929510004,
"count": 97,
"self": 253.389231347006,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.2032616039944,
"count": 2910,
"self": 66.2032616039944
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6200001482502557e-06,
"count": 1,
"self": 1.6200001482502557e-06
},
"TrainerController._save_models": {
"total": 0.16968109000026743,
"count": 1,
"self": 0.0029133759999240283,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1667677140003434,
"count": 1,
"self": 0.1667677140003434
}
}
}
}
}
}
}