Haitao Gao
First Push
2acdfa2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9047507047653198,
"min": 0.9047507047653198,
"max": 2.8615331649780273,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8638.5595703125,
"min": 8638.5595703125,
"max": 29399.390625,
"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": 13.12868595123291,
"min": 0.47958987951278687,
"max": 13.12868595123291,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2560.09375,
"min": 93.04043579101562,
"max": 2664.8271484375,
"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": 0.0697963807837921,
"min": 0.06382300355380364,
"max": 0.07622592353955934,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2791855231351684,
"min": 0.25680733549105594,
"max": 0.38112961769779674,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19527731762797224,
"min": 0.10565202904627749,
"max": 0.27493385485574307,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7811092705118889,
"min": 0.42260811618510996,
"max": 1.3746692742787154,
"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": 26.09090909090909,
"min": 2.9545454545454546,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1148.0,
"min": 130.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.09090909090909,
"min": 2.9545454545454546,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1148.0,
"min": 130.0,
"max": 1418.0,
"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": "1691839234",
"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": "1691839736"
},
"total": 501.975556471,
"count": 1,
"self": 0.4335820630000171,
"children": {
"run_training.setup": {
"total": 0.0516426830000114,
"count": 1,
"self": 0.0516426830000114
},
"TrainerController.start_learning": {
"total": 501.490331725,
"count": 1,
"self": 0.5641858799929764,
"children": {
"TrainerController._reset_env": {
"total": 4.029976315999988,
"count": 1,
"self": 4.029976315999988
},
"TrainerController.advance": {
"total": 496.734357867007,
"count": 18201,
"self": 0.2790811110054392,
"children": {
"env_step": {
"total": 496.4552767560016,
"count": 18201,
"self": 363.3221319789979,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.8434074299994,
"count": 18201,
"self": 1.8660668280019195,
"children": {
"TorchPolicy.evaluate": {
"total": 130.97734060199747,
"count": 18201,
"self": 130.97734060199747
}
}
},
"workers": {
"total": 0.28973734700429077,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 499.713101306,
"count": 18201,
"is_parallel": true,
"self": 235.33697645900088,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006129806000046756,
"count": 1,
"is_parallel": true,
"self": 0.004430162000005566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016996440000411894,
"count": 10,
"is_parallel": true,
"self": 0.0016996440000411894
}
}
},
"UnityEnvironment.step": {
"total": 0.061133668000024954,
"count": 1,
"is_parallel": true,
"self": 0.0005142599999885533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003319529999998849,
"count": 1,
"is_parallel": true,
"self": 0.0003319529999998849
},
"communicator.exchange": {
"total": 0.05774946000002501,
"count": 1,
"is_parallel": true,
"self": 0.05774946000002501
},
"steps_from_proto": {
"total": 0.002537995000011506,
"count": 1,
"is_parallel": true,
"self": 0.000439025000048332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002098969999963174,
"count": 10,
"is_parallel": true,
"self": 0.002098969999963174
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 264.3761248469991,
"count": 18200,
"is_parallel": true,
"self": 10.98070142599181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.628557097006478,
"count": 18200,
"is_parallel": true,
"self": 5.628557097006478
},
"communicator.exchange": {
"total": 208.23326884900325,
"count": 18200,
"is_parallel": true,
"self": 208.23326884900325
},
"steps_from_proto": {
"total": 39.53359747499758,
"count": 18200,
"is_parallel": true,
"self": 7.194559812975626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.33903766202195,
"count": 182000,
"is_parallel": true,
"self": 32.33903766202195
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014469899997493485,
"count": 1,
"self": 0.00014469899997493485,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 492.77607621395697,
"count": 462162,
"is_parallel": true,
"self": 10.807347298950333,
"children": {
"process_trajectory": {
"total": 271.0728406610075,
"count": 462162,
"is_parallel": true,
"self": 270.26983423800743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8030064230000562,
"count": 4,
"is_parallel": true,
"self": 0.8030064230000562
}
}
},
"_update_policy": {
"total": 210.89588825399915,
"count": 90,
"is_parallel": true,
"self": 86.90068886699976,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.99519938699939,
"count": 4587,
"is_parallel": true,
"self": 123.99519938699939
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.16166696300001604,
"count": 1,
"self": 0.0008680959999765037,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16079886700003954,
"count": 1,
"self": 0.16079886700003954
}
}
}
}
}
}
}