pcapp's picture
Initial run
9834290
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9609087109565735,
"min": 0.9531342387199402,
"max": 2.8667008876800537,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9185.326171875,
"min": 9185.326171875,
"max": 29389.41796875,
"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": 12.879825592041016,
"min": 0.26969483494758606,
"max": 12.879825592041016,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.56591796875,
"min": 52.32080078125,
"max": 2605.46484375,
"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": 0.07709415880084385,
"min": 0.05841787479199839,
"max": 0.0797439214629669,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3083766352033754,
"min": 0.23367149916799357,
"max": 0.39871960731483447,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1982503894935636,
"min": 0.10968273074831814,
"max": 0.27873697781971857,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7930015579742544,
"min": 0.43873092299327254,
"max": 1.3501899853056551,
"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": 25.136363636363637,
"min": 3.3863636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 149.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.3863636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 149.0,
"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": "1689612247",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1689612786"
},
"total": 538.924210054,
"count": 1,
"self": 0.4334199820000322,
"children": {
"run_training.setup": {
"total": 0.043489880999970865,
"count": 1,
"self": 0.043489880999970865
},
"TrainerController.start_learning": {
"total": 538.447300191,
"count": 1,
"self": 0.7314638060012157,
"children": {
"TrainerController._reset_env": {
"total": 4.220874643999991,
"count": 1,
"self": 4.220874643999991
},
"TrainerController.advance": {
"total": 533.3269959199987,
"count": 18201,
"self": 0.33690032599531605,
"children": {
"env_step": {
"total": 532.9900955940034,
"count": 18201,
"self": 387.78164050402034,
"children": {
"SubprocessEnvManager._take_step": {
"total": 144.8574231110025,
"count": 18201,
"self": 2.20839844901343,
"children": {
"TorchPolicy.evaluate": {
"total": 142.64902466198907,
"count": 18201,
"self": 142.64902466198907
}
}
},
"workers": {
"total": 0.3510319789805294,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 536.5630572360074,
"count": 18201,
"is_parallel": true,
"self": 248.5058124690064,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007102809000002708,
"count": 1,
"is_parallel": true,
"self": 0.0051480960000276355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019547129999750723,
"count": 10,
"is_parallel": true,
"self": 0.0019547129999750723
}
}
},
"UnityEnvironment.step": {
"total": 0.049799623000012616,
"count": 1,
"is_parallel": true,
"self": 0.000647989000015059,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038116100000706865,
"count": 1,
"is_parallel": true,
"self": 0.00038116100000706865
},
"communicator.exchange": {
"total": 0.0462479720000033,
"count": 1,
"is_parallel": true,
"self": 0.0462479720000033
},
"steps_from_proto": {
"total": 0.0025225009999871872,
"count": 1,
"is_parallel": true,
"self": 0.0004466490000254453,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002075851999961742,
"count": 10,
"is_parallel": true,
"self": 0.002075851999961742
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 288.05724476700095,
"count": 18200,
"is_parallel": true,
"self": 11.832800195999255,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.161524789994587,
"count": 18200,
"is_parallel": true,
"self": 6.161524789994587
},
"communicator.exchange": {
"total": 227.74987037999773,
"count": 18200,
"is_parallel": true,
"self": 227.74987037999773
},
"steps_from_proto": {
"total": 42.31304940100938,
"count": 18200,
"is_parallel": true,
"self": 7.818502901019542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.49454649998984,
"count": 182000,
"is_parallel": true,
"self": 34.49454649998984
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022185800003171607,
"count": 1,
"self": 0.00022185800003171607,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 529.0874370400594,
"count": 508167,
"is_parallel": true,
"self": 11.929127739077444,
"children": {
"process_trajectory": {
"total": 294.14030613498153,
"count": 508167,
"is_parallel": true,
"self": 292.5330992769815,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6072068580000405,
"count": 4,
"is_parallel": true,
"self": 1.6072068580000405
}
}
},
"_update_policy": {
"total": 223.01800316600048,
"count": 90,
"is_parallel": true,
"self": 83.80158596600035,
"children": {
"TorchPPOOptimizer.update": {
"total": 139.21641720000014,
"count": 4587,
"is_parallel": true,
"self": 139.21641720000014
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1677439630000208,
"count": 1,
"self": 0.0009305329999733658,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16681343000004745,
"count": 1,
"self": 0.16681343000004745
}
}
}
}
}
}
}