cway140's picture
First Push
6d95842 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9807544946670532,
"min": 0.9807544946670532,
"max": 2.865377426147461,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9321.0908203125,
"min": 9321.0908203125,
"max": 29249.7734375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.619028091430664,
"min": 0.3772943913936615,
"max": 12.619028091430664,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2460.71044921875,
"min": 73.19511413574219,
"max": 2552.07373046875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06821771055903952,
"min": 0.06387666836321039,
"max": 0.07532984720534182,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2728708422361581,
"min": 0.25550667345284156,
"max": 0.373318048615771,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22182427218877804,
"min": 0.11540736420554859,
"max": 0.311493431002486,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8872970887551122,
"min": 0.46162945682219436,
"max": 1.55746715501243,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.84090909090909,
"min": 3.1363636363636362,
"max": 25.163636363636364,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 138.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.1363636363636362,
"max": 25.163636363636364,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 138.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1769052864",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1769053302"
},
"total": 437.751420101,
"count": 1,
"self": 0.44334833599998547,
"children": {
"run_training.setup": {
"total": 0.02593236600000637,
"count": 1,
"self": 0.02593236600000637
},
"TrainerController.start_learning": {
"total": 437.282139399,
"count": 1,
"self": 0.39977454099573606,
"children": {
"TrainerController._reset_env": {
"total": 3.205957153999975,
"count": 1,
"self": 3.205957153999975
},
"TrainerController.advance": {
"total": 433.6010730940043,
"count": 18192,
"self": 0.39998937000200385,
"children": {
"env_step": {
"total": 315.8235981199955,
"count": 18192,
"self": 247.1941211410001,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.39345268399768,
"count": 18192,
"self": 1.2839298509943546,
"children": {
"TorchPolicy.evaluate": {
"total": 67.10952283300333,
"count": 18192,
"self": 67.10952283300333
}
}
},
"workers": {
"total": 0.23602429499771915,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.6497242560042,
"count": 18192,
"is_parallel": true,
"self": 219.0920501349974,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005229729000006955,
"count": 1,
"is_parallel": true,
"self": 0.003630810999879941,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015989180001270142,
"count": 10,
"is_parallel": true,
"self": 0.0015989180001270142
}
}
},
"UnityEnvironment.step": {
"total": 0.034848085000021456,
"count": 1,
"is_parallel": true,
"self": 0.000627442000109113,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003958510000074966,
"count": 1,
"is_parallel": true,
"self": 0.0003958510000074966
},
"communicator.exchange": {
"total": 0.03188187599994308,
"count": 1,
"is_parallel": true,
"self": 0.03188187599994308
},
"steps_from_proto": {
"total": 0.0019429159999617696,
"count": 1,
"is_parallel": true,
"self": 0.000347668999893358,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015952470000684116,
"count": 10,
"is_parallel": true,
"self": 0.0015952470000684116
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.5576741210068,
"count": 18191,
"is_parallel": true,
"self": 10.295167630029937,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.407632923983556,
"count": 18191,
"is_parallel": true,
"self": 5.407632923983556
},
"communicator.exchange": {
"total": 165.17009378799276,
"count": 18191,
"is_parallel": true,
"self": 165.17009378799276
},
"steps_from_proto": {
"total": 35.684779779000564,
"count": 18191,
"is_parallel": true,
"self": 6.69627324000146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.988506538999104,
"count": 181910,
"is_parallel": true,
"self": 28.988506538999104
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.37748560400678,
"count": 18192,
"self": 0.49442107301740634,
"children": {
"process_trajectory": {
"total": 26.00934524798822,
"count": 18192,
"self": 25.58910692298855,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42023832499967284,
"count": 4,
"self": 0.42023832499967284
}
}
},
"_update_policy": {
"total": 90.87371928300115,
"count": 90,
"self": 37.426745008995226,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.446974274005925,
"count": 4587,
"self": 53.446974274005925
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.329999102192232e-07,
"count": 1,
"self": 9.329999102192232e-07
},
"TrainerController._save_models": {
"total": 0.07533367700011695,
"count": 1,
"self": 0.0007881770002313715,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07454549999988558,
"count": 1,
"self": 0.07454549999988558
}
}
}
}
}
}
}