yonghonglin's picture
First Push
5f59489 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9388294219970703,
"min": 0.8798625469207764,
"max": 2.8541274070739746,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8922.634765625,
"min": 8641.00390625,
"max": 29134.931640625,
"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": 13.217628479003906,
"min": 0.5712912082672119,
"max": 13.217628479003906,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2577.4375,
"min": 110.83049011230469,
"max": 2665.71728515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06767013729504291,
"min": 0.06498746069196118,
"max": 0.07497632127556511,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27068054918017165,
"min": 0.26385802066343944,
"max": 0.36515011618144394,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1953797047482986,
"min": 0.10257642540633313,
"max": 0.27491362750822423,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7815188189931944,
"min": 0.41030570162533253,
"max": 1.3083151619808346,
"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": 26.454545454545453,
"min": 3.2045454545454546,
"max": 26.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1164.0,
"min": 141.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.454545454545453,
"min": 3.2045454545454546,
"max": 26.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1164.0,
"min": 141.0,
"max": 1429.0,
"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": "1741159112",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741159547"
},
"total": 435.416857048,
"count": 1,
"self": 0.4383854059999521,
"children": {
"run_training.setup": {
"total": 0.02316873300003408,
"count": 1,
"self": 0.02316873300003408
},
"TrainerController.start_learning": {
"total": 434.955302909,
"count": 1,
"self": 0.38136893201999555,
"children": {
"TrainerController._reset_env": {
"total": 2.8806629910000083,
"count": 1,
"self": 2.8806629910000083
},
"TrainerController.advance": {
"total": 431.59556117798,
"count": 18192,
"self": 0.37726450197135364,
"children": {
"env_step": {
"total": 303.98300030601706,
"count": 18192,
"self": 232.21639509398312,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.55115016401612,
"count": 18192,
"self": 1.2624981570196496,
"children": {
"TorchPolicy.evaluate": {
"total": 70.28865200699647,
"count": 18192,
"self": 70.28865200699647
}
}
},
"workers": {
"total": 0.2154550480178159,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.3913571970104,
"count": 18192,
"is_parallel": true,
"self": 229.8514864000316,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050160189999814975,
"count": 1,
"is_parallel": true,
"self": 0.003539608999972188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014764100000093094,
"count": 10,
"is_parallel": true,
"self": 0.0014764100000093094
}
}
},
"UnityEnvironment.step": {
"total": 0.03683464300002015,
"count": 1,
"is_parallel": true,
"self": 0.0006050380001170197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003819849999899816,
"count": 1,
"is_parallel": true,
"self": 0.0003819849999899816
},
"communicator.exchange": {
"total": 0.03392953699994905,
"count": 1,
"is_parallel": true,
"self": 0.03392953699994905
},
"steps_from_proto": {
"total": 0.0019180829999640991,
"count": 1,
"is_parallel": true,
"self": 0.00039323400017110544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015248489997929937,
"count": 10,
"is_parallel": true,
"self": 0.0015248489997929937
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 203.5398707969788,
"count": 18191,
"is_parallel": true,
"self": 9.601570832965876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.338750261004066,
"count": 18191,
"is_parallel": true,
"self": 5.338750261004066
},
"communicator.exchange": {
"total": 157.55031486599137,
"count": 18191,
"is_parallel": true,
"self": 157.55031486599137
},
"steps_from_proto": {
"total": 31.04923483701748,
"count": 18191,
"is_parallel": true,
"self": 5.5945472710074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.45468756601008,
"count": 181910,
"is_parallel": true,
"self": 25.45468756601008
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.2352963699916,
"count": 18192,
"self": 0.4494377679772015,
"children": {
"process_trajectory": {
"total": 27.156842678014186,
"count": 18192,
"self": 26.583530612014215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5733120659999713,
"count": 4,
"self": 0.5733120659999713
}
}
},
"_update_policy": {
"total": 99.62901592400021,
"count": 90,
"self": 41.159643269002686,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.46937265499753,
"count": 4587,
"self": 58.46937265499753
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.41999963085982e-07,
"count": 1,
"self": 8.41999963085982e-07
},
"TrainerController._save_models": {
"total": 0.09770896600002743,
"count": 1,
"self": 0.0009068930000921682,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09680207299993526,
"count": 1,
"self": 0.09680207299993526
}
}
}
}
}
}
}