mcamara's picture
First Push
785a33c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0160609483718872,
"min": 1.0160609483718872,
"max": 2.8649144172668457,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9701.349609375,
"min": 9701.349609375,
"max": 29402.6171875,
"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": 12.713342666625977,
"min": 0.3422013521194458,
"max": 12.713342666625977,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2479.101806640625,
"min": 66.3870620727539,
"max": 2519.09814453125,
"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": 0.06679655067159283,
"min": 0.061396020447764564,
"max": 0.07186658917379682,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26718620268637133,
"min": 0.2610970564721855,
"max": 0.3593329458689841,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1884362174965003,
"min": 0.12269892058946996,
"max": 0.2689013888036796,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7537448699860012,
"min": 0.49079568235787985,
"max": 1.3445069440183979,
"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": 25.363636363636363,
"min": 3.409090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 150.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.409090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 150.0,
"max": 1385.0,
"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": "1688479410",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688479876"
},
"total": 465.46757251,
"count": 1,
"self": 0.43994420600000694,
"children": {
"run_training.setup": {
"total": 0.03960223399997176,
"count": 1,
"self": 0.03960223399997176
},
"TrainerController.start_learning": {
"total": 464.98802607000005,
"count": 1,
"self": 0.5273062989890605,
"children": {
"TrainerController._reset_env": {
"total": 3.9851554640000018,
"count": 1,
"self": 3.9851554640000018
},
"TrainerController.advance": {
"total": 460.33563128901113,
"count": 18200,
"self": 0.2594446900160392,
"children": {
"env_step": {
"total": 460.0761865989951,
"count": 18200,
"self": 335.30034101999803,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.51642458199473,
"count": 18200,
"self": 1.708591870997168,
"children": {
"TorchPolicy.evaluate": {
"total": 122.80783271099756,
"count": 18200,
"self": 122.80783271099756
}
}
},
"workers": {
"total": 0.2594209970023371,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.44189732899315,
"count": 18200,
"is_parallel": true,
"self": 218.10438950098734,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0070685929999854125,
"count": 1,
"is_parallel": true,
"self": 0.00444644499992819,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002622148000057223,
"count": 10,
"is_parallel": true,
"self": 0.002622148000057223
}
}
},
"UnityEnvironment.step": {
"total": 0.03650404899997284,
"count": 1,
"is_parallel": true,
"self": 0.0006144879999965269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000322616999994807,
"count": 1,
"is_parallel": true,
"self": 0.000322616999994807
},
"communicator.exchange": {
"total": 0.03325730899996415,
"count": 1,
"is_parallel": true,
"self": 0.03325730899996415
},
"steps_from_proto": {
"total": 0.0023096350000173516,
"count": 1,
"is_parallel": true,
"self": 0.0003922800000850657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019173549999322859,
"count": 10,
"is_parallel": true,
"self": 0.0019173549999322859
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.3375078280058,
"count": 18199,
"is_parallel": true,
"self": 10.335982701015666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.286843054002645,
"count": 18199,
"is_parallel": true,
"self": 5.286843054002645
},
"communicator.exchange": {
"total": 194.43284557599566,
"count": 18199,
"is_parallel": true,
"self": 194.43284557599566
},
"steps_from_proto": {
"total": 35.28183649699184,
"count": 18199,
"is_parallel": true,
"self": 6.3416969410162665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.940139555975577,
"count": 181990,
"is_parallel": true,
"self": 28.940139555975577
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.6263999959373905e-05,
"count": 1,
"self": 3.6263999959373905e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.85324069604457,
"count": 434585,
"is_parallel": true,
"self": 9.71257590902718,
"children": {
"process_trajectory": {
"total": 251.49742451701712,
"count": 434585,
"is_parallel": true,
"self": 249.96065660301707,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5367679140000519,
"count": 4,
"is_parallel": true,
"self": 1.5367679140000519
}
}
},
"_update_policy": {
"total": 195.64324027000026,
"count": 90,
"is_parallel": true,
"self": 76.33540559099941,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.30783467900085,
"count": 4584,
"is_parallel": true,
"self": 119.30783467900085
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1398967539998921,
"count": 1,
"self": 0.0009140349998233432,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13898271900006876,
"count": 1,
"self": 0.13898271900006876
}
}
}
}
}
}
}