Nostradamused's picture
First Push
b8c0b23
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8278598785400391,
"min": 0.8278598785400391,
"max": 2.868229389190674,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7904.40625,
"min": 7904.40625,
"max": 29341.986328125,
"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": 12.704962730407715,
"min": 0.3364443778991699,
"max": 12.704962730407715,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2477.4677734375,
"min": 65.27021026611328,
"max": 2566.556640625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06786088616354391,
"min": 0.06321428402135258,
"max": 0.07824270849211162,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27144354465417564,
"min": 0.2619039416749729,
"max": 0.3742847800661134,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19725992873895404,
"min": 0.11051944259088486,
"max": 0.27710048246617414,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7890397149558162,
"min": 0.44207777036353946,
"max": 1.3855024123308706,
"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.CumulativeReward.mean": {
"value": 25.431818181818183,
"min": 3.5,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 154.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 3.5,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 154.0,
"max": 1379.0,
"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": "1700430906",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700431374"
},
"total": 468.67259679100005,
"count": 1,
"self": 0.4303154120001409,
"children": {
"run_training.setup": {
"total": 0.04638605799993911,
"count": 1,
"self": 0.04638605799993911
},
"TrainerController.start_learning": {
"total": 468.19589532099997,
"count": 1,
"self": 0.5411391760044353,
"children": {
"TrainerController._reset_env": {
"total": 10.015810052000006,
"count": 1,
"self": 10.015810052000006
},
"TrainerController.advance": {
"total": 457.5500033229954,
"count": 18199,
"self": 0.2603214679949133,
"children": {
"env_step": {
"total": 457.2896818550005,
"count": 18199,
"self": 317.06203313600395,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.96117956900446,
"count": 18199,
"self": 1.3943882959980556,
"children": {
"TorchPolicy.evaluate": {
"total": 138.5667912730064,
"count": 18199,
"self": 138.5667912730064
}
}
},
"workers": {
"total": 0.2664691499920764,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 467.0008265959933,
"count": 18199,
"is_parallel": true,
"self": 230.5947246679949,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005772865999915666,
"count": 1,
"is_parallel": true,
"self": 0.003449619999855713,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002323246000059953,
"count": 10,
"is_parallel": true,
"self": 0.002323246000059953
}
}
},
"UnityEnvironment.step": {
"total": 0.04358767899998384,
"count": 1,
"is_parallel": true,
"self": 0.0005695290000176101,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039210199997796735,
"count": 1,
"is_parallel": true,
"self": 0.00039210199997796735
},
"communicator.exchange": {
"total": 0.040820599999960905,
"count": 1,
"is_parallel": true,
"self": 0.040820599999960905
},
"steps_from_proto": {
"total": 0.0018054480000273543,
"count": 1,
"is_parallel": true,
"self": 0.00034733699999378587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014581110000335684,
"count": 10,
"is_parallel": true,
"self": 0.0014581110000335684
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.4061019279984,
"count": 18198,
"is_parallel": true,
"self": 10.327169563995426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3021928109996,
"count": 18198,
"is_parallel": true,
"self": 5.3021928109996
},
"communicator.exchange": {
"total": 187.9880694980036,
"count": 18198,
"is_parallel": true,
"self": 187.9880694980036
},
"steps_from_proto": {
"total": 32.788670054999784,
"count": 18198,
"is_parallel": true,
"self": 6.007416105970947,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.781253949028837,
"count": 181980,
"is_parallel": true,
"self": 26.781253949028837
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001662950000991259,
"count": 1,
"self": 0.0001662950000991259,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 453.70541912999374,
"count": 478781,
"is_parallel": true,
"self": 9.968735414061598,
"children": {
"process_trajectory": {
"total": 255.51208144493194,
"count": 478781,
"is_parallel": true,
"self": 254.9904179219318,
"children": {
"RLTrainer._checkpoint": {
"total": 0.521663523000143,
"count": 4,
"is_parallel": true,
"self": 0.521663523000143
}
}
},
"_update_policy": {
"total": 188.2246022710002,
"count": 90,
"is_parallel": true,
"self": 66.27110491800636,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.95349735299385,
"count": 4587,
"is_parallel": true,
"self": 121.95349735299385
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0887764750000315,
"count": 1,
"self": 0.0008288240001093072,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08794765099992219,
"count": 1,
"self": 0.08794765099992219
}
}
}
}
}
}
}