futuromelon's picture
First Push
fabc84a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8312448859214783,
"min": 0.8312448859214783,
"max": 2.8389031887054443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7900.1513671875,
"min": 7900.1513671875,
"max": 28979.5234375,
"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": 13.470294952392578,
"min": 0.4360419511795044,
"max": 13.470294952392578,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2626.70751953125,
"min": 84.5921401977539,
"max": 2748.59033203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.09678187634539534,
"min": 0.0893590563541372,
"max": 0.10193061985761126,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.38712750538158136,
"min": 0.3574362254165488,
"max": 0.5085037939539796,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20212950894937795,
"min": 0.13641007397898244,
"max": 0.2738853318068911,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8085180357975118,
"min": 0.5456402959159298,
"max": 1.3001986116170883,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382799997,
"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": 0.9617200000000001,
"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": 26.113636363636363,
"min": 4.136363636363637,
"max": 26.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1149.0,
"min": 182.0,
"max": 1446.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.113636363636363,
"min": 4.136363636363637,
"max": 26.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1149.0,
"min": 182.0,
"max": 1446.0,
"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": "1730743869",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730744443"
},
"total": 574.071830805,
"count": 1,
"self": 0.4439957859999595,
"children": {
"run_training.setup": {
"total": 0.0544113710000147,
"count": 1,
"self": 0.0544113710000147
},
"TrainerController.start_learning": {
"total": 573.573423648,
"count": 1,
"self": 0.34497418098294474,
"children": {
"TrainerController._reset_env": {
"total": 2.4557194900000923,
"count": 1,
"self": 2.4557194900000923
},
"TrainerController.advance": {
"total": 570.6880146000171,
"count": 18192,
"self": 0.3567256820329021,
"children": {
"env_step": {
"total": 292.5749179730044,
"count": 18192,
"self": 223.1761342949883,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.19592140101327,
"count": 18192,
"self": 1.2157505330164895,
"children": {
"TorchPolicy.evaluate": {
"total": 67.98017086799678,
"count": 18192,
"self": 67.98017086799678
}
}
},
"workers": {
"total": 0.20286227700285053,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 572.2134377729981,
"count": 18192,
"is_parallel": true,
"self": 376.64408054902174,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00219493000008697,
"count": 1,
"is_parallel": true,
"self": 0.000665914999672168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015290150004148018,
"count": 10,
"is_parallel": true,
"self": 0.0015290150004148018
}
}
},
"UnityEnvironment.step": {
"total": 0.057126649000110774,
"count": 1,
"is_parallel": true,
"self": 0.0006454440001562034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040940700000646757,
"count": 1,
"is_parallel": true,
"self": 0.00040940700000646757
},
"communicator.exchange": {
"total": 0.05425884999999653,
"count": 1,
"is_parallel": true,
"self": 0.05425884999999653
},
"steps_from_proto": {
"total": 0.0018129479999515752,
"count": 1,
"is_parallel": true,
"self": 0.0003393370000139839,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014736109999375913,
"count": 10,
"is_parallel": true,
"self": 0.0014736109999375913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.56935722397634,
"count": 18191,
"is_parallel": true,
"self": 9.76644749196953,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.568276940014357,
"count": 18191,
"is_parallel": true,
"self": 5.568276940014357
},
"communicator.exchange": {
"total": 149.4949139279945,
"count": 18191,
"is_parallel": true,
"self": 149.4949139279945
},
"steps_from_proto": {
"total": 30.73971886399795,
"count": 18191,
"is_parallel": true,
"self": 5.524681026016879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.215037837981072,
"count": 181910,
"is_parallel": true,
"self": 25.215037837981072
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 277.75637094497984,
"count": 18192,
"self": 0.4138050089834451,
"children": {
"process_trajectory": {
"total": 27.05419059999599,
"count": 18192,
"self": 26.63383311399616,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4203574859998298,
"count": 4,
"self": 0.4203574859998298
}
}
},
"_update_policy": {
"total": 250.2883753360004,
"count": 90,
"self": 70.8761108260112,
"children": {
"TorchPPOOptimizer.update": {
"total": 179.4122645099892,
"count": 15295,
"self": 179.4122645099892
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.650000265537528e-07,
"count": 1,
"self": 9.650000265537528e-07
},
"TrainerController._save_models": {
"total": 0.084714411999812,
"count": 1,
"self": 0.0011005939998085523,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08361381800000345,
"count": 1,
"self": 0.08361381800000345
}
}
}
}
}
}
}