s14pe's picture
First Push
31c0799 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.4943733811378479,
"min": 0.4943733811378479,
"max": 0.7056332230567932,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5019.373046875,
"min": 4754.6962890625,
"max": 7218.6279296875,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 799960.0,
"min": 409984.0,
"max": 799960.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 799960.0,
"min": 409984.0,
"max": 799960.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.808820724487305,
"min": 13.193782806396484,
"max": 13.85569953918457,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2692.719970703125,
"min": 2520.936279296875,
"max": 2823.49072265625,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0663299566770672,
"min": 0.05895930239086168,
"max": 0.07579412799047228,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2653198267082688,
"min": 0.25395220195887125,
"max": 0.37227309237156686,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18863208303410633,
"min": 0.16949746781120112,
"max": 0.21578454467760144,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7545283321364253,
"min": 0.7056388096774325,
"max": 1.0642197091205448,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.8615993794999968e-06,
"min": 1.8615993794999968e-06,
"max": 0.0001478865507045,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 7.446397517999987e-06,
"min": 7.446397517999987e-06,
"max": 0.00072087025971,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10062050000000002,
"min": 0.10062050000000002,
"max": 0.1492955,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40248200000000006,
"min": 0.40248200000000006,
"max": 0.7402900000000001,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.096294999999994e-05,
"min": 4.096294999999994e-05,
"max": 0.0024698454500000004,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00016385179999999977,
"min": 0.00016385179999999977,
"max": 0.012040471,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.977272727272727,
"min": 25.25,
"max": 27.236363636363638,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1187.0,
"min": 1111.0,
"max": 1498.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.977272727272727,
"min": 25.25,
"max": 27.236363636363638,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1187.0,
"min": 1111.0,
"max": 1498.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709830399",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709831237"
},
"total": 837.1549888989998,
"count": 1,
"self": 0.4249774029995024,
"children": {
"run_training.setup": {
"total": 0.04806337599984545,
"count": 1,
"self": 0.04806337599984545
},
"TrainerController.start_learning": {
"total": 836.6819481200005,
"count": 1,
"self": 1.5146177680098845,
"children": {
"TrainerController._reset_env": {
"total": 1.5567412420000437,
"count": 1,
"self": 1.5567412420000437
},
"TrainerController.advance": {
"total": 833.5426764609911,
"count": 36397,
"self": 0.7135625310434079,
"children": {
"env_step": {
"total": 832.8291139299477,
"count": 36397,
"self": 636.6612743369333,
"children": {
"SubprocessEnvManager._take_step": {
"total": 195.47259186800602,
"count": 36397,
"self": 3.5238584719686514,
"children": {
"TorchPolicy.evaluate": {
"total": 191.94873339603737,
"count": 36397,
"self": 191.94873339603737
}
}
},
"workers": {
"total": 0.6952477250083575,
"count": 36397,
"self": 0.0,
"children": {
"worker_root": {
"total": 833.9606951660485,
"count": 36397,
"is_parallel": true,
"self": 372.5757268059756,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0014738099998794496,
"count": 1,
"is_parallel": true,
"self": 0.00036711999882754753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001106690001051902,
"count": 10,
"is_parallel": true,
"self": 0.001106690001051902
}
}
},
"UnityEnvironment.step": {
"total": 0.034364247000212345,
"count": 1,
"is_parallel": true,
"self": 0.0006592500003534951,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004073999998581712,
"count": 1,
"is_parallel": true,
"self": 0.0004073999998581712
},
"communicator.exchange": {
"total": 0.03139416700014408,
"count": 1,
"is_parallel": true,
"self": 0.03139416700014408
},
"steps_from_proto": {
"total": 0.0019034299998565984,
"count": 1,
"is_parallel": true,
"self": 0.0003646899990599195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001538740000796679,
"count": 10,
"is_parallel": true,
"self": 0.001538740000796679
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 461.3849683600729,
"count": 36396,
"is_parallel": true,
"self": 22.765330977275426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 12.194953916924987,
"count": 36396,
"is_parallel": true,
"self": 12.194953916924987
},
"communicator.exchange": {
"total": 362.10607452691966,
"count": 36396,
"is_parallel": true,
"self": 362.10607452691966
},
"steps_from_proto": {
"total": 64.31860893895282,
"count": 36396,
"is_parallel": true,
"self": 12.983445099156597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 51.33516383979622,
"count": 363960,
"is_parallel": true,
"self": 51.33516383979622
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0004932299998472445,
"count": 1,
"self": 0.0004932299998472445,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 824.3154142171288,
"count": 1305699,
"is_parallel": true,
"self": 24.275280504980856,
"children": {
"process_trajectory": {
"total": 465.16101738014595,
"count": 1305699,
"is_parallel": true,
"self": 464.14467385114676,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0163435289991867,
"count": 8,
"is_parallel": true,
"self": 1.0163435289991867
}
}
},
"_update_policy": {
"total": 334.879116332002,
"count": 181,
"is_parallel": true,
"self": 79.05680358999325,
"children": {
"TorchPPOOptimizer.update": {
"total": 255.82231274200876,
"count": 9219,
"is_parallel": true,
"self": 255.82231274200876
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.06741941899963422,
"count": 1,
"self": 0.0021931800001766533,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06522623899945756,
"count": 1,
"self": 0.06522623899945756
}
}
}
}
}
}
}