Esteban00007's picture
First Push
4f50270 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1152541637420654,
"min": 1.1152541637420654,
"max": 2.8692986965179443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10685.25,
"min": 10685.25,
"max": 29479.17578125,
"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": 12.714330673217773,
"min": 0.4835585653781891,
"max": 12.714330673217773,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2479.29443359375,
"min": 93.81036376953125,
"max": 2577.3251953125,
"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": 0.07007500012353857,
"min": 0.06074562048751806,
"max": 0.07376007269771186,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28030000049415427,
"min": 0.2580044508213177,
"max": 0.36880036348855927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18650591775190595,
"min": 0.08937574561694454,
"max": 0.29639174117177136,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7460236710076238,
"min": 0.3575029824677782,
"max": 1.3907665934632805,
"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": 25.022727272727273,
"min": 2.8863636363636362,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1101.0,
"min": 127.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.022727272727273,
"min": 2.8863636363636362,
"max": 25.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1101.0,
"min": 127.0,
"max": 1377.0,
"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": "1734441596",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1734442255"
},
"total": 659.02322499,
"count": 1,
"self": 0.3219780569999102,
"children": {
"run_training.setup": {
"total": 0.04001494500005265,
"count": 1,
"self": 0.04001494500005265
},
"TrainerController.start_learning": {
"total": 658.661231988,
"count": 1,
"self": 0.5211371800118059,
"children": {
"TrainerController._reset_env": {
"total": 4.818494326000064,
"count": 1,
"self": 4.818494326000064
},
"TrainerController.advance": {
"total": 653.259673002988,
"count": 18207,
"self": 0.28025525698444653,
"children": {
"env_step": {
"total": 652.9794177460036,
"count": 18207,
"self": 532.7076825159943,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.00253045400552,
"count": 18207,
"self": 1.8557459560272491,
"children": {
"TorchPolicy.evaluate": {
"total": 118.14678449797827,
"count": 18207,
"self": 118.14678449797827
}
}
},
"workers": {
"total": 0.26920477600378945,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 657.7767461830047,
"count": 18207,
"is_parallel": true,
"self": 222.73907708399872,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022857430000158274,
"count": 1,
"is_parallel": true,
"self": 0.0007008149998455337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015849280001702937,
"count": 10,
"is_parallel": true,
"self": 0.0015849280001702937
}
}
},
"UnityEnvironment.step": {
"total": 0.029426540999907047,
"count": 1,
"is_parallel": true,
"self": 0.0005607849999478276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002594649999991816,
"count": 1,
"is_parallel": true,
"self": 0.0002594649999991816
},
"communicator.exchange": {
"total": 0.027092799000001833,
"count": 1,
"is_parallel": true,
"self": 0.027092799000001833
},
"steps_from_proto": {
"total": 0.0015134919999582053,
"count": 1,
"is_parallel": true,
"self": 0.0002844569997932922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001229035000164913,
"count": 10,
"is_parallel": true,
"self": 0.001229035000164913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 435.03766909900594,
"count": 18206,
"is_parallel": true,
"self": 10.958363208996502,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3958097260094746,
"count": 18206,
"is_parallel": true,
"self": 3.3958097260094746
},
"communicator.exchange": {
"total": 374.7650211519981,
"count": 18206,
"is_parallel": true,
"self": 374.7650211519981
},
"steps_from_proto": {
"total": 45.91847501200186,
"count": 18206,
"is_parallel": true,
"self": 6.88491745703061,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.03355755497125,
"count": 182060,
"is_parallel": true,
"self": 39.03355755497125
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00020223800015628512,
"count": 1,
"self": 0.00020223800015628512,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 652.6752581980155,
"count": 214174,
"is_parallel": true,
"self": 2.769937606990993,
"children": {
"process_trajectory": {
"total": 367.14297991202386,
"count": 214174,
"is_parallel": true,
"self": 366.3529750440239,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7900048679999827,
"count": 4,
"is_parallel": true,
"self": 0.7900048679999827
}
}
},
"_update_policy": {
"total": 282.76234067900066,
"count": 90,
"is_parallel": true,
"self": 36.66741357899832,
"children": {
"TorchPPOOptimizer.update": {
"total": 246.09492710000234,
"count": 4584,
"is_parallel": true,
"self": 246.09492710000234
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.06172524099997645,
"count": 1,
"self": 0.0009278339998672891,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06079740700010916,
"count": 1,
"self": 0.06079740700010916
}
}
}
}
}
}
}