NEO946B's picture
First Push
4fb2f9d
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.071456789970398,
"min": 1.071456789970398,
"max": 2.844573736190796,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10312.771484375,
"min": 10312.771484375,
"max": 29193.859375,
"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": 12.784031867980957,
"min": 0.318082720041275,
"max": 12.784031867980957,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2492.88623046875,
"min": 61.708045959472656,
"max": 2578.489501953125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06650428860816379,
"min": 0.06262839294572856,
"max": 0.07361140547311115,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26601715443265517,
"min": 0.25454189006396677,
"max": 0.3680570273655558,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22875415855178644,
"min": 0.12178783709361382,
"max": 0.291595451825974,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9150166342071457,
"min": 0.4871513483744553,
"max": 1.360000425986215,
"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": 25.295454545454547,
"min": 3.4318181818181817,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 151.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.4318181818181817,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 151.0,
"max": 1375.0,
"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": "1691563164",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691563633"
},
"total": 469.042702169,
"count": 1,
"self": 0.7920080000001235,
"children": {
"run_training.setup": {
"total": 0.04165162000003875,
"count": 1,
"self": 0.04165162000003875
},
"TrainerController.start_learning": {
"total": 468.20904254899983,
"count": 1,
"self": 0.5456807749856125,
"children": {
"TrainerController._reset_env": {
"total": 5.49506729299992,
"count": 1,
"self": 5.49506729299992
},
"TrainerController.advance": {
"total": 461.9393347790144,
"count": 18222,
"self": 0.27120015103650985,
"children": {
"env_step": {
"total": 461.6681346279779,
"count": 18222,
"self": 338.0490923839934,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.34466948100408,
"count": 18222,
"self": 1.8877377260018875,
"children": {
"TorchPolicy.evaluate": {
"total": 121.45693175500219,
"count": 18222,
"self": 121.45693175500219
}
}
},
"workers": {
"total": 0.2743727629804198,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.5845390350098,
"count": 18222,
"is_parallel": true,
"self": 221.3771348979949,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006191203000071255,
"count": 1,
"is_parallel": true,
"self": 0.004627771000059511,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001563432000011744,
"count": 10,
"is_parallel": true,
"self": 0.001563432000011744
}
}
},
"UnityEnvironment.step": {
"total": 0.09822219300008328,
"count": 1,
"is_parallel": true,
"self": 0.0006907340000452677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005423860000064451,
"count": 1,
"is_parallel": true,
"self": 0.0005423860000064451
},
"communicator.exchange": {
"total": 0.09483878700007153,
"count": 1,
"is_parallel": true,
"self": 0.09483878700007153
},
"steps_from_proto": {
"total": 0.0021502859999600332,
"count": 1,
"is_parallel": true,
"self": 0.0003675580001072376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017827279998527956,
"count": 10,
"is_parallel": true,
"self": 0.0017827279998527956
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.20740413701492,
"count": 18221,
"is_parallel": true,
"self": 10.44484626101007,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.251183132012329,
"count": 18221,
"is_parallel": true,
"self": 5.251183132012329
},
"communicator.exchange": {
"total": 193.85403074399665,
"count": 18221,
"is_parallel": true,
"self": 193.85403074399665
},
"steps_from_proto": {
"total": 35.657343999995874,
"count": 18221,
"is_parallel": true,
"self": 6.443075286900012,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.214268713095862,
"count": 182210,
"is_parallel": true,
"self": 29.214268713095862
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013165699988348933,
"count": 1,
"self": 0.00013165699988348933,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.46307104497396,
"count": 426081,
"is_parallel": true,
"self": 9.538686747876682,
"children": {
"process_trajectory": {
"total": 250.33487453609837,
"count": 426081,
"is_parallel": true,
"self": 248.68105240409864,
"children": {
"RLTrainer._checkpoint": {
"total": 1.653822131999732,
"count": 4,
"is_parallel": true,
"self": 1.653822131999732
}
}
},
"_update_policy": {
"total": 198.5895097609989,
"count": 90,
"is_parallel": true,
"self": 80.51330034699981,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.0762094139991,
"count": 4587,
"is_parallel": true,
"self": 118.0762094139991
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2288280450000002,
"count": 1,
"self": 0.001123200999927576,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22770484400007263,
"count": 1,
"self": 0.22770484400007263
}
}
}
}
}
}
}