gael1130's picture
First Push
8a7b2c6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.45326828956604,
"min": 1.45326828956604,
"max": 2.8856496810913086,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 13907.77734375,
"min": 13907.77734375,
"max": 29678.90625,
"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": 12.03728199005127,
"min": 0.07058456540107727,
"max": 12.03728199005127,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2347.27001953125,
"min": 13.693405151367188,
"max": 2416.7978515625,
"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.Environment.CumulativeReward.mean": {
"value": 25.25,
"min": 2.840909090909091,
"max": 25.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 125.0,
"max": 1356.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 2.840909090909091,
"max": 25.25,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 125.0,
"max": 1356.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.04913099060421718,
"min": 0.04365610457984183,
"max": 0.05619956936025833,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09826198120843437,
"min": 0.08731220915968366,
"max": 0.1514836644317827,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22043375028114692,
"min": 0.08999519286832462,
"max": 0.2956534274945072,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.44086750056229385,
"min": 0.17999038573664924,
"max": 0.7987751166025797,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.432097856000005e-06,
"min": 6.432097856000005e-06,
"max": 0.00029023200325600004,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.286419571200001e-05,
"min": 1.286419571200001e-05,
"max": 0.0007419960526679999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.101072,
"min": 0.101072,
"max": 0.148372,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.202144,
"min": 0.202144,
"max": 0.423666,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.410560000000004e-05,
"min": 7.410560000000004e-05,
"max": 0.0029026456,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00014821120000000008,
"min": 0.00014821120000000008,
"max": 0.0074252268,
"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": "1711287342",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711287868"
},
"total": 525.2966360710002,
"count": 1,
"self": 0.8646911680004905,
"children": {
"run_training.setup": {
"total": 0.06278789199996027,
"count": 1,
"self": 0.06278789199996027
},
"TrainerController.start_learning": {
"total": 524.3691570109997,
"count": 1,
"self": 0.7244436890118777,
"children": {
"TrainerController._reset_env": {
"total": 3.590322783000147,
"count": 1,
"self": 3.590322783000147
},
"TrainerController.advance": {
"total": 519.8278352569878,
"count": 18215,
"self": 0.35436361693791696,
"children": {
"env_step": {
"total": 519.4734716400499,
"count": 18215,
"self": 337.9324151430144,
"children": {
"SubprocessEnvManager._take_step": {
"total": 181.17407005802124,
"count": 18215,
"self": 1.721974152996836,
"children": {
"TorchPolicy.evaluate": {
"total": 179.4520959050244,
"count": 18215,
"self": 179.4520959050244
}
}
},
"workers": {
"total": 0.36698643901422656,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 522.7557384389895,
"count": 18215,
"is_parallel": true,
"self": 267.0560238890023,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009607822999896598,
"count": 1,
"is_parallel": true,
"self": 0.005565542999647732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004042280000248866,
"count": 10,
"is_parallel": true,
"self": 0.004042280000248866
}
}
},
"UnityEnvironment.step": {
"total": 0.0396600970000236,
"count": 1,
"is_parallel": true,
"self": 0.0007879069999034982,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046169600000212085,
"count": 1,
"is_parallel": true,
"self": 0.00046169600000212085
},
"communicator.exchange": {
"total": 0.03620720200001415,
"count": 1,
"is_parallel": true,
"self": 0.03620720200001415
},
"steps_from_proto": {
"total": 0.002203292000103829,
"count": 1,
"is_parallel": true,
"self": 0.0004364830003851239,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017668089997187053,
"count": 10,
"is_parallel": true,
"self": 0.0017668089997187053
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.69971454998722,
"count": 18214,
"is_parallel": true,
"self": 11.994450352980039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.203864561994351,
"count": 18214,
"is_parallel": true,
"self": 6.203864561994351
},
"communicator.exchange": {
"total": 199.57690301201592,
"count": 18214,
"is_parallel": true,
"self": 199.57690301201592
},
"steps_from_proto": {
"total": 37.92449662299691,
"count": 18214,
"is_parallel": true,
"self": 7.478734652990852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.44576197000606,
"count": 182140,
"is_parallel": true,
"self": 30.44576197000606
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017136299993580906,
"count": 1,
"self": 0.00017136299993580906,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 511.92425896008376,
"count": 919327,
"is_parallel": true,
"self": 20.685323797968067,
"children": {
"process_trajectory": {
"total": 361.9015667131164,
"count": 919327,
"is_parallel": true,
"self": 360.5856844281161,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3158822850002707,
"count": 4,
"is_parallel": true,
"self": 1.3158822850002707
}
}
},
"_update_policy": {
"total": 129.3373684489993,
"count": 45,
"is_parallel": true,
"self": 53.39528914399875,
"children": {
"TorchPPOOptimizer.update": {
"total": 75.94207930500056,
"count": 2292,
"is_parallel": true,
"self": 75.94207930500056
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22638391899999988,
"count": 1,
"self": 0.0017769050000424613,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22460701399995742,
"count": 1,
"self": 0.22460701399995742
}
}
}
}
}
}
}