BubbleJoe's picture
First Push
00d6d31
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8537280559539795,
"min": 0.8502798676490784,
"max": 2.87601637840271,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8151.3955078125,
"min": 8151.3955078125,
"max": 29611.46484375,
"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": 12.76717472076416,
"min": 0.3704228401184082,
"max": 12.775993347167969,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2489.59912109375,
"min": 71.86203002929688,
"max": 2606.302734375,
"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": 0.06953825216310089,
"min": 0.06073783055049431,
"max": 0.07676455206964616,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27815300865240355,
"min": 0.24295132220197724,
"max": 0.3838227603482308,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17875877435446952,
"min": 0.10059340491630686,
"max": 0.2847011404878953,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7150350974178781,
"min": 0.40237361966522744,
"max": 1.4040262386494993,
"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": 25.09090909090909,
"min": 2.9318181818181817,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 129.0,
"max": 1384.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 2.9318181818181817,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 129.0,
"max": 1384.0,
"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": "1694526410",
"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": "1694526904"
},
"total": 493.862200504,
"count": 1,
"self": 0.436305515000015,
"children": {
"run_training.setup": {
"total": 0.06960553100003608,
"count": 1,
"self": 0.06960553100003608
},
"TrainerController.start_learning": {
"total": 493.35628945799994,
"count": 1,
"self": 0.5622461900029521,
"children": {
"TrainerController._reset_env": {
"total": 4.711803918000044,
"count": 1,
"self": 4.711803918000044
},
"TrainerController.advance": {
"total": 487.90799603199696,
"count": 18201,
"self": 0.2789438049843511,
"children": {
"env_step": {
"total": 487.6290522270126,
"count": 18201,
"self": 354.0882111660064,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.25279986400074,
"count": 18201,
"self": 1.8617380809993165,
"children": {
"TorchPolicy.evaluate": {
"total": 131.39106178300142,
"count": 18201,
"self": 131.39106178300142
}
}
},
"workers": {
"total": 0.2880411970054979,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 491.7718613639995,
"count": 18201,
"is_parallel": true,
"self": 231.7116489340114,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00689864700001408,
"count": 1,
"is_parallel": true,
"self": 0.00447521700004927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00242342999996481,
"count": 10,
"is_parallel": true,
"self": 0.00242342999996481
}
}
},
"UnityEnvironment.step": {
"total": 0.05197152499999902,
"count": 1,
"is_parallel": true,
"self": 0.0005328690000965253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000442192999969393,
"count": 1,
"is_parallel": true,
"self": 0.000442192999969393
},
"communicator.exchange": {
"total": 0.04804664599998887,
"count": 1,
"is_parallel": true,
"self": 0.04804664599998887
},
"steps_from_proto": {
"total": 0.0029498169999442325,
"count": 1,
"is_parallel": true,
"self": 0.0013213739998718665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001628443000072366,
"count": 10,
"is_parallel": true,
"self": 0.001628443000072366
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.0602124299881,
"count": 18200,
"is_parallel": true,
"self": 10.892225682988055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.866734868001799,
"count": 18200,
"is_parallel": true,
"self": 5.866734868001799
},
"communicator.exchange": {
"total": 204.20743344199315,
"count": 18200,
"is_parallel": true,
"self": 204.20743344199315
},
"steps_from_proto": {
"total": 39.0938184370051,
"count": 18200,
"is_parallel": true,
"self": 7.035013316019672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.058805120985426,
"count": 182000,
"is_parallel": true,
"self": 32.058805120985426
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018233100001907587,
"count": 1,
"self": 0.00018233100001907587,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 483.89876460600436,
"count": 446055,
"is_parallel": true,
"self": 10.609064172036028,
"children": {
"process_trajectory": {
"total": 266.61969301396823,
"count": 446055,
"is_parallel": true,
"self": 265.2683412449683,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3513517689999048,
"count": 4,
"is_parallel": true,
"self": 1.3513517689999048
}
}
},
"_update_policy": {
"total": 206.6700074200001,
"count": 90,
"is_parallel": true,
"self": 79.85657746399744,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.81342995600266,
"count": 4587,
"is_parallel": true,
"self": 126.81342995600266
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17406098699996164,
"count": 1,
"self": 0.0008994869999696675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17316149999999197,
"count": 1,
"self": 0.17316149999999197
}
}
}
}
}
}
}