SwarajRay's picture
ppo snowball unit5
29804f3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9589532017707825,
"min": 0.9541028141975403,
"max": 2.8689563274383545,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9156.0849609375,
"min": 9156.0849609375,
"max": 29412.5390625,
"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": 13.136601448059082,
"min": 0.3393712639808655,
"max": 13.136601448059082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2561.63720703125,
"min": 65.83802795410156,
"max": 2658.681640625,
"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": 0.07348203951465514,
"min": 0.062137068954411116,
"max": 0.0748907312292003,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29392815805862055,
"min": 0.24854827581764447,
"max": 0.3744536561460015,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20557291345561252,
"min": 0.11816055997156118,
"max": 0.26552103328354215,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8222916538224501,
"min": 0.4726422398862447,
"max": 1.3203356634168064,
"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": 25.613636363636363,
"min": 3.1363636363636362,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 138.0,
"max": 1425.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.1363636363636362,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 138.0,
"max": 1425.0,
"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": "1720100330",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720100900"
},
"total": 570.062346005,
"count": 1,
"self": 0.485732252000048,
"children": {
"run_training.setup": {
"total": 0.06221368900003199,
"count": 1,
"self": 0.06221368900003199
},
"TrainerController.start_learning": {
"total": 569.5144000639999,
"count": 1,
"self": 0.7965340830188552,
"children": {
"TrainerController._reset_env": {
"total": 3.294191273000024,
"count": 1,
"self": 3.294191273000024
},
"TrainerController.advance": {
"total": 565.306354084981,
"count": 18201,
"self": 0.4126648099804697,
"children": {
"env_step": {
"total": 564.8936892750005,
"count": 18201,
"self": 371.49719653899126,
"children": {
"SubprocessEnvManager._take_step": {
"total": 192.99422439201953,
"count": 18201,
"self": 1.9856591070382592,
"children": {
"TorchPolicy.evaluate": {
"total": 191.00856528498127,
"count": 18201,
"self": 191.00856528498127
}
}
},
"workers": {
"total": 0.4022683439897037,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 567.8112293309842,
"count": 18201,
"is_parallel": true,
"self": 280.0725107689731,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006733948000032797,
"count": 1,
"is_parallel": true,
"self": 0.0048205679999000495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019133800001327472,
"count": 10,
"is_parallel": true,
"self": 0.0019133800001327472
}
}
},
"UnityEnvironment.step": {
"total": 0.11123000899999624,
"count": 1,
"is_parallel": true,
"self": 0.0008171439999387076,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004665200000317782,
"count": 1,
"is_parallel": true,
"self": 0.0004665200000317782
},
"communicator.exchange": {
"total": 0.10739137500002016,
"count": 1,
"is_parallel": true,
"self": 0.10739137500002016
},
"steps_from_proto": {
"total": 0.0025549700000055964,
"count": 1,
"is_parallel": true,
"self": 0.0005114079998520538,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020435620001535426,
"count": 10,
"is_parallel": true,
"self": 0.0020435620001535426
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 287.7387185620112,
"count": 18200,
"is_parallel": true,
"self": 13.227571108036614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.814312247988937,
"count": 18200,
"is_parallel": true,
"self": 6.814312247988937
},
"communicator.exchange": {
"total": 224.7535323269899,
"count": 18200,
"is_parallel": true,
"self": 224.7535323269899
},
"steps_from_proto": {
"total": 42.94330287899572,
"count": 18200,
"is_parallel": true,
"self": 8.422281122997106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.52102175599862,
"count": 182000,
"is_parallel": true,
"self": 34.52102175599862
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016892300004656136,
"count": 1,
"self": 0.00016892300004656136,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 557.9391359391092,
"count": 842854,
"is_parallel": true,
"self": 19.121790799039218,
"children": {
"process_trajectory": {
"total": 313.44105057007016,
"count": 842854,
"is_parallel": true,
"self": 312.68016890107015,
"children": {
"RLTrainer._checkpoint": {
"total": 0.760881669000014,
"count": 4,
"is_parallel": true,
"self": 0.760881669000014
}
}
},
"_update_policy": {
"total": 225.3762945699998,
"count": 90,
"is_parallel": true,
"self": 68.60635179499502,
"children": {
"TorchPPOOptimizer.update": {
"total": 156.76994277500478,
"count": 4587,
"is_parallel": true,
"self": 156.76994277500478
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11715170000002217,
"count": 1,
"self": 0.001503595000031055,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11564810499999112,
"count": 1,
"self": 0.11564810499999112
}
}
}
}
}
}
}