mathreader's picture
First Training of SnowballTarget
b97269c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9785627126693726,
"min": 0.9626041650772095,
"max": 2.860818862915039,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9375.609375,
"min": 9375.609375,
"max": 29360.583984375,
"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": 12.93183708190918,
"min": 0.3186158537864685,
"max": 12.93183708190918,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.708251953125,
"min": 61.81147766113281,
"max": 2605.0224609375,
"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": 0.07070022170128319,
"min": 0.05834946902334695,
"max": 0.07756551966874622,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28280088680513277,
"min": 0.2333978760933878,
"max": 0.38782759834373115,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20843180743794815,
"min": 0.11717436773766417,
"max": 0.2705112021343381,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8337272297517926,
"min": 0.46869747095065667,
"max": 1.3525560106716905,
"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": 25.931818181818183,
"min": 3.272727272727273,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 144.0,
"max": 1378.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.272727272727273,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 144.0,
"max": 1378.0,
"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": "1707894977",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707895361"
},
"total": 384.1442753409999,
"count": 1,
"self": 0.3221323739999207,
"children": {
"run_training.setup": {
"total": 0.048576903000025595,
"count": 1,
"self": 0.048576903000025595
},
"TrainerController.start_learning": {
"total": 383.77356606399997,
"count": 1,
"self": 0.5240884690163057,
"children": {
"TrainerController._reset_env": {
"total": 2.8308916199999885,
"count": 1,
"self": 2.8308916199999885
},
"TrainerController.advance": {
"total": 380.32710530798363,
"count": 18202,
"self": 0.25555261695501486,
"children": {
"env_step": {
"total": 380.0715526910286,
"count": 18202,
"self": 258.47297381101885,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.3404298990007,
"count": 18202,
"self": 1.4325130339883572,
"children": {
"TorchPolicy.evaluate": {
"total": 119.90791686501234,
"count": 18202,
"self": 119.90791686501234
}
}
},
"workers": {
"total": 0.2581489810090716,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 383.0983796669914,
"count": 18202,
"is_parallel": true,
"self": 193.28247572101498,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002114196000093216,
"count": 1,
"is_parallel": true,
"self": 0.0006388810000999001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014753149999933157,
"count": 10,
"is_parallel": true,
"self": 0.0014753149999933157
}
}
},
"UnityEnvironment.step": {
"total": 0.02787149400000999,
"count": 1,
"is_parallel": true,
"self": 0.000446480000050542,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002804200000809942,
"count": 1,
"is_parallel": true,
"self": 0.0002804200000809942
},
"communicator.exchange": {
"total": 0.02590655999995306,
"count": 1,
"is_parallel": true,
"self": 0.02590655999995306
},
"steps_from_proto": {
"total": 0.001238033999925392,
"count": 1,
"is_parallel": true,
"self": 0.0002654799997117152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009725540002136768,
"count": 10,
"is_parallel": true,
"self": 0.0009725540002136768
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 189.8159039459764,
"count": 18201,
"is_parallel": true,
"self": 7.907152385990798,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.0239217499884035,
"count": 18201,
"is_parallel": true,
"self": 4.0239217499884035
},
"communicator.exchange": {
"total": 154.10933693700656,
"count": 18201,
"is_parallel": true,
"self": 154.10933693700656
},
"steps_from_proto": {
"total": 23.77549287299064,
"count": 18201,
"is_parallel": true,
"self": 4.56720146699206,
"children": {
"_process_rank_one_or_two_observation": {
"total": 19.20829140599858,
"count": 182010,
"is_parallel": true,
"self": 19.20829140599858
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015688300004512712,
"count": 1,
"self": 0.00015688300004512712,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 379.0179485639719,
"count": 268402,
"is_parallel": true,
"self": 4.474958136083501,
"children": {
"process_trajectory": {
"total": 211.5573030188874,
"count": 268402,
"is_parallel": true,
"self": 211.05758744388743,
"children": {
"RLTrainer._checkpoint": {
"total": 0.499715574999982,
"count": 4,
"is_parallel": true,
"self": 0.499715574999982
}
}
},
"_update_policy": {
"total": 162.985687409001,
"count": 90,
"is_parallel": true,
"self": 37.03279468600181,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.9528927229992,
"count": 4587,
"is_parallel": true,
"self": 125.9528927229992
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09132378399999652,
"count": 1,
"self": 0.0009376440000323782,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09038613999996414,
"count": 1,
"self": 0.09038613999996414
}
}
}
}
}
}
}