shahafw's picture
First Push
7ee5ea8
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0653297901153564,
"min": 1.0653297901153564,
"max": 2.858488082885742,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10183.4873046875,
"min": 10183.4873046875,
"max": 29273.77734375,
"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": 12.638876914978027,
"min": 0.36404725909233093,
"max": 12.638876914978027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2464.5810546875,
"min": 70.62516784667969,
"max": 2563.384765625,
"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": 0.06756832470066501,
"min": 0.06126134650320654,
"max": 0.07445792262716328,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27027329880266004,
"min": 0.24504538601282616,
"max": 0.3722896131358164,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2581539674132478,
"min": 0.15281490772259515,
"max": 0.2732131793072411,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0326158696529912,
"min": 0.6112596308903806,
"max": 1.3492888837468389,
"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": 24.886363636363637,
"min": 3.772727272727273,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 166.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.772727272727273,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 166.0,
"max": 1370.0,
"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": "1686387464",
"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=SnowballTarget --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": "1686387940"
},
"total": 476.149789041,
"count": 1,
"self": 0.4313932070000419,
"children": {
"run_training.setup": {
"total": 0.043099917999995796,
"count": 1,
"self": 0.043099917999995796
},
"TrainerController.start_learning": {
"total": 475.675295916,
"count": 1,
"self": 0.6231617049925262,
"children": {
"TrainerController._reset_env": {
"total": 4.137711034999995,
"count": 1,
"self": 4.137711034999995
},
"TrainerController.advance": {
"total": 470.78015949700756,
"count": 18204,
"self": 0.2754055160073108,
"children": {
"env_step": {
"total": 470.50475398100025,
"count": 18204,
"self": 345.81845625501,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.40468182899639,
"count": 18204,
"self": 1.8459019109993164,
"children": {
"TorchPolicy.evaluate": {
"total": 122.55877991799707,
"count": 18204,
"self": 122.55877991799707
}
}
},
"workers": {
"total": 0.28161589699382716,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.10254149799437,
"count": 18204,
"is_parallel": true,
"self": 220.06562533399813,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005703778999986753,
"count": 1,
"is_parallel": true,
"self": 0.004112338999959775,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001591440000026978,
"count": 10,
"is_parallel": true,
"self": 0.001591440000026978
}
}
},
"UnityEnvironment.step": {
"total": 0.052595511999982136,
"count": 1,
"is_parallel": true,
"self": 0.0006636710000123003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003221030000020164,
"count": 1,
"is_parallel": true,
"self": 0.0003221030000020164
},
"communicator.exchange": {
"total": 0.04946189399998957,
"count": 1,
"is_parallel": true,
"self": 0.04946189399998957
},
"steps_from_proto": {
"total": 0.0021478439999782495,
"count": 1,
"is_parallel": true,
"self": 0.0003648979999297808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017829460000484687,
"count": 10,
"is_parallel": true,
"self": 0.0017829460000484687
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.03691616399624,
"count": 18203,
"is_parallel": true,
"self": 10.576325412007378,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3421877689913515,
"count": 18203,
"is_parallel": true,
"self": 5.3421877689913515
},
"communicator.exchange": {
"total": 203.22721400599457,
"count": 18203,
"is_parallel": true,
"self": 203.22721400599457
},
"steps_from_proto": {
"total": 34.89118897700294,
"count": 18203,
"is_parallel": true,
"self": 6.285768090999568,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.605420886003373,
"count": 182030,
"is_parallel": true,
"self": 28.605420886003373
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001696159999937663,
"count": 1,
"self": 0.0001696159999937663,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 467.0786967380349,
"count": 462394,
"is_parallel": true,
"self": 9.9716951830531,
"children": {
"process_trajectory": {
"total": 255.84439582698175,
"count": 462394,
"is_parallel": true,
"self": 254.98892250198176,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8554733249999913,
"count": 4,
"is_parallel": true,
"self": 0.8554733249999913
}
}
},
"_update_policy": {
"total": 201.26260572800004,
"count": 90,
"is_parallel": true,
"self": 78.3491579639983,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.91344776400175,
"count": 4587,
"is_parallel": true,
"self": 122.91344776400175
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13409406299990678,
"count": 1,
"self": 0.0009151099999371581,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13317895299996962,
"count": 1,
"self": 0.13317895299996962
}
}
}
}
}
}
}