happycoding's picture
First training of SnowballTarget
e163374
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.174038052558899,
"min": 1.174038052558899,
"max": 2.8678956031799316,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11209.71484375,
"min": 11209.71484375,
"max": 29370.119140625,
"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": 12.44819164276123,
"min": 0.3220609426498413,
"max": 12.44819164276123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2427.3974609375,
"min": 62.479820251464844,
"max": 2511.388671875,
"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": 0.06750314029255498,
"min": 0.06287782924770213,
"max": 0.072123610793856,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27001256117021993,
"min": 0.25613389462848907,
"max": 0.3493247595982051,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19507435178932023,
"min": 0.12411809559048646,
"max": 0.2712084866621915,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7802974071572809,
"min": 0.49647238236194585,
"max": 1.2449745630516726,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.954545454545453,
"min": 3.7045454545454546,
"max": 24.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 163.0,
"max": 1333.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.7045454545454546,
"max": 24.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 163.0,
"max": 1333.0,
"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": "1673955403",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673956072"
},
"total": 669.4317232669999,
"count": 1,
"self": 0.44422402500003955,
"children": {
"run_training.setup": {
"total": 0.1320815199999288,
"count": 1,
"self": 0.1320815199999288
},
"TrainerController.start_learning": {
"total": 668.855417722,
"count": 1,
"self": 0.8173208230293767,
"children": {
"TrainerController._reset_env": {
"total": 7.40299329100003,
"count": 1,
"self": 7.40299329100003
},
"TrainerController.advance": {
"total": 660.4412189859705,
"count": 18203,
"self": 0.4253443039647209,
"children": {
"env_step": {
"total": 660.0158746820058,
"count": 18203,
"self": 458.52880868001796,
"children": {
"SubprocessEnvManager._take_step": {
"total": 201.07569101098125,
"count": 18203,
"self": 2.2252586409892956,
"children": {
"TorchPolicy.evaluate": {
"total": 198.85043236999195,
"count": 18203,
"self": 43.61234312499528,
"children": {
"TorchPolicy.sample_actions": {
"total": 155.23808924499667,
"count": 18203,
"self": 155.23808924499667
}
}
}
}
},
"workers": {
"total": 0.41137499100659625,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 666.8028849499884,
"count": 18203,
"is_parallel": true,
"self": 352.5673122799833,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022758769999882134,
"count": 1,
"is_parallel": true,
"self": 0.0007870730003105564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001488803999677657,
"count": 10,
"is_parallel": true,
"self": 0.001488803999677657
}
}
},
"UnityEnvironment.step": {
"total": 0.04247787100007372,
"count": 1,
"is_parallel": true,
"self": 0.0004530470000645437,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030941900001835165,
"count": 1,
"is_parallel": true,
"self": 0.00030941900001835165
},
"communicator.exchange": {
"total": 0.03739513300001818,
"count": 1,
"is_parallel": true,
"self": 0.03739513300001818
},
"steps_from_proto": {
"total": 0.004320271999972647,
"count": 1,
"is_parallel": true,
"self": 0.0024280349999799,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018922369999927469,
"count": 10,
"is_parallel": true,
"self": 0.0018922369999927469
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 314.2355726700051,
"count": 18202,
"is_parallel": true,
"self": 11.973910423041957,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.102371408989484,
"count": 18202,
"is_parallel": true,
"self": 7.102371408989484
},
"communicator.exchange": {
"total": 248.52160051998032,
"count": 18202,
"is_parallel": true,
"self": 248.52160051998032
},
"steps_from_proto": {
"total": 46.63769031799336,
"count": 18202,
"is_parallel": true,
"self": 10.312700045041652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.32499027295171,
"count": 182020,
"is_parallel": true,
"self": 36.32499027295171
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.5978000091272406e-05,
"count": 1,
"self": 5.5978000091272406e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 655.2431680850985,
"count": 515361,
"is_parallel": true,
"self": 15.649296385115235,
"children": {
"process_trajectory": {
"total": 336.8250515159839,
"count": 515361,
"is_parallel": true,
"self": 335.4416910359839,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3833604799999648,
"count": 4,
"is_parallel": true,
"self": 1.3833604799999648
}
}
},
"_update_policy": {
"total": 302.7688201839994,
"count": 90,
"is_parallel": true,
"self": 82.85062497199965,
"children": {
"TorchPPOOptimizer.update": {
"total": 219.91819521199977,
"count": 7645,
"is_parallel": true,
"self": 219.91819521199977
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19382864399995015,
"count": 1,
"self": 0.001489240999944741,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1923394030000054,
"count": 1,
"self": 0.1923394030000054
}
}
}
}
}
}
}