JSlin's picture
First Push
97c69ee verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9203991889953613,
"min": 0.9132375121116638,
"max": 2.8556604385375977,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8747.4736328125,
"min": 8747.4736328125,
"max": 29150.58203125,
"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": 13.107122421264648,
"min": 0.22698140144348145,
"max": 13.145352363586426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2555.888916015625,
"min": 44.034393310546875,
"max": 2681.65185546875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06222460122494251,
"min": 0.06222460122494251,
"max": 0.07471619951475969,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24889840489977005,
"min": 0.24889840489977005,
"max": 0.3735809975737984,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18381838858419774,
"min": 0.09978993895849414,
"max": 0.28992607700181944,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.735273554336791,
"min": 0.39915975583397656,
"max": 1.4195933093627293,
"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": 25.636363636363637,
"min": 2.75,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 121.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 2.75,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 121.0,
"max": 1409.0,
"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": "1748417769",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748418227"
},
"total": 457.4714316210001,
"count": 1,
"self": 0.4411839189999682,
"children": {
"run_training.setup": {
"total": 0.024063405999982024,
"count": 1,
"self": 0.024063405999982024
},
"TrainerController.start_learning": {
"total": 457.00618429600013,
"count": 1,
"self": 0.3971441130064477,
"children": {
"TrainerController._reset_env": {
"total": 3.3593736260000924,
"count": 1,
"self": 3.3593736260000924
},
"TrainerController.advance": {
"total": 453.1537711829935,
"count": 18192,
"self": 0.41891101999613056,
"children": {
"env_step": {
"total": 321.3779671119976,
"count": 18192,
"self": 246.09917646800773,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.04599034998046,
"count": 18192,
"self": 1.3486497769702055,
"children": {
"TorchPolicy.evaluate": {
"total": 73.69734057301025,
"count": 18192,
"self": 73.69734057301025
}
}
},
"workers": {
"total": 0.23280029400939384,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.5264101749791,
"count": 18192,
"is_parallel": true,
"self": 239.4479190130079,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005154340999979468,
"count": 1,
"is_parallel": true,
"self": 0.003519881999864083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016344590001153847,
"count": 10,
"is_parallel": true,
"self": 0.0016344590001153847
}
}
},
"UnityEnvironment.step": {
"total": 0.03762165400007689,
"count": 1,
"is_parallel": true,
"self": 0.0005806230001326185,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004024140000637999,
"count": 1,
"is_parallel": true,
"self": 0.0004024140000637999
},
"communicator.exchange": {
"total": 0.03485717900002783,
"count": 1,
"is_parallel": true,
"self": 0.03485717900002783
},
"steps_from_proto": {
"total": 0.001781437999852642,
"count": 1,
"is_parallel": true,
"self": 0.00037057899999126676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014108589998613752,
"count": 10,
"is_parallel": true,
"self": 0.0014108589998613752
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.07849116197121,
"count": 18191,
"is_parallel": true,
"self": 10.366721837022396,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.612651664975374,
"count": 18191,
"is_parallel": true,
"self": 5.612651664975374
},
"communicator.exchange": {
"total": 167.1547873219845,
"count": 18191,
"is_parallel": true,
"self": 167.1547873219845
},
"steps_from_proto": {
"total": 32.94433033798896,
"count": 18191,
"is_parallel": true,
"self": 5.935215980944804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.009114357044155,
"count": 181910,
"is_parallel": true,
"self": 27.009114357044155
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.35689305099982,
"count": 18192,
"self": 0.5077915340086747,
"children": {
"process_trajectory": {
"total": 28.61876792899193,
"count": 18192,
"self": 28.186561582992,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4322063459999299,
"count": 4,
"self": 0.4322063459999299
}
}
},
"_update_policy": {
"total": 102.23033358799921,
"count": 90,
"self": 41.88739601600173,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.34293757199748,
"count": 4587,
"self": 60.34293757199748
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.320000688399887e-07,
"count": 1,
"self": 8.320000688399887e-07
},
"TrainerController._save_models": {
"total": 0.09589454199999636,
"count": 1,
"self": 0.0007760250000501401,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09511851699994622,
"count": 1,
"self": 0.09511851699994622
}
}
}
}
}
}
}