Augcos's picture
first commit
60f7af3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8948683738708496,
"min": 0.8948683738708496,
"max": 2.864894390106201,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8544.203125,
"min": 8544.203125,
"max": 29496.953125,
"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": 13.101550102233887,
"min": 0.3455760180950165,
"max": 13.101550102233887,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.80224609375,
"min": 67.041748046875,
"max": 2657.208251953125,
"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": 0.07217235190721255,
"min": 0.060509807923089666,
"max": 0.07217235190721255,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2886894076288502,
"min": 0.2658771936023864,
"max": 0.3579066950444351,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2042530051195154,
"min": 0.11225665915373932,
"max": 0.2990770651137128,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8170120204780617,
"min": 0.4490266366149573,
"max": 1.3606354536707785,
"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": 25.545454545454547,
"min": 3.2954545454545454,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 145.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.2954545454545454,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 145.0,
"max": 1406.0,
"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": "1681203233",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681203692"
},
"total": 459.5742143729999,
"count": 1,
"self": 0.43141732799983856,
"children": {
"run_training.setup": {
"total": 0.19713316499996836,
"count": 1,
"self": 0.19713316499996836
},
"TrainerController.start_learning": {
"total": 458.9456638800001,
"count": 1,
"self": 0.5252589359994317,
"children": {
"TrainerController._reset_env": {
"total": 3.7799343589999808,
"count": 1,
"self": 3.7799343589999808
},
"TrainerController.advance": {
"total": 454.5098642930009,
"count": 18201,
"self": 0.27350640900704093,
"children": {
"env_step": {
"total": 454.23635788399383,
"count": 18201,
"self": 332.22699939999256,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.73551862000284,
"count": 18201,
"self": 1.631303657999183,
"children": {
"TorchPolicy.evaluate": {
"total": 120.10421496200365,
"count": 18201,
"self": 120.10421496200365
}
}
},
"workers": {
"total": 0.2738398639984325,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.4700726449935,
"count": 18201,
"is_parallel": true,
"self": 213.68197036499225,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004985200000078294,
"count": 1,
"is_parallel": true,
"self": 0.0035354510001752715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014497489999030222,
"count": 10,
"is_parallel": true,
"self": 0.0014497489999030222
}
}
},
"UnityEnvironment.step": {
"total": 0.035081301999980496,
"count": 1,
"is_parallel": true,
"self": 0.0006206029999020757,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045972700002039346,
"count": 1,
"is_parallel": true,
"self": 0.00045972700002039346
},
"communicator.exchange": {
"total": 0.032057034999979805,
"count": 1,
"is_parallel": true,
"self": 0.032057034999979805
},
"steps_from_proto": {
"total": 0.001943937000078222,
"count": 1,
"is_parallel": true,
"self": 0.00041466000038781203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015292769996904099,
"count": 10,
"is_parallel": true,
"self": 0.0015292769996904099
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.78810228000123,
"count": 18200,
"is_parallel": true,
"self": 9.979110522007772,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.471921968992433,
"count": 18200,
"is_parallel": true,
"self": 5.471921968992433
},
"communicator.exchange": {
"total": 195.93189503099802,
"count": 18200,
"is_parallel": true,
"self": 195.93189503099802
},
"steps_from_proto": {
"total": 32.405174758003,
"count": 18200,
"is_parallel": true,
"self": 6.356547435007997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.048627322995003,
"count": 182000,
"is_parallel": true,
"self": 26.048627322995003
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001305189998674905,
"count": 1,
"self": 0.0001305189998674905,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 451.2810468659935,
"count": 388193,
"is_parallel": true,
"self": 9.39223744599542,
"children": {
"process_trajectory": {
"total": 248.2630246109985,
"count": 388193,
"is_parallel": true,
"self": 247.0523621099984,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2106625010001153,
"count": 4,
"is_parallel": true,
"self": 1.2106625010001153
}
}
},
"_update_policy": {
"total": 193.62578480899958,
"count": 90,
"is_parallel": true,
"self": 73.44987633599908,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.1759084730005,
"count": 4584,
"is_parallel": true,
"self": 120.1759084730005
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13047577299994373,
"count": 1,
"self": 0.0008787559997927019,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12959701700015103,
"count": 1,
"self": 0.12959701700015103
}
}
}
}
}
}
}