tylerkiser's picture
First Push
54b33cd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6576073169708252,
"min": 0.6252917051315308,
"max": 2.875319004058838,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6264.3671875,
"min": 5956.52880859375,
"max": 29541.02734375,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.251148223876953,
"min": 0.46528303623199463,
"max": 14.464152336120605,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2778.973876953125,
"min": 90.26490783691406,
"max": 2950.68701171875,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06902610237411151,
"min": 0.05924993521866604,
"max": 0.07675161727573533,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27610440949644605,
"min": 0.24386721686231813,
"max": 0.37392903391075527,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1671445503757865,
"min": 0.1116097148590009,
"max": 0.32504030813773477,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.668578201503146,
"min": 0.4464388594360036,
"max": 1.300161232550939,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.2940995412000045e-06,
"min": 2.2940995412000045e-06,
"max": 0.0004972940005412001,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 9.176398164800018e-06,
"min": 9.176398164800018e-06,
"max": 0.002461720007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.1994588,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.992344,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000004e-05,
"min": 3.289412000000004e-05,
"max": 0.00497299412,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00013157648000000017,
"min": 0.00013157648000000017,
"max": 0.0246179656,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.177777777777777,
"min": 2.7954545454545454,
"max": 28.522727272727273,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1223.0,
"min": 123.0,
"max": 1564.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.177777777777777,
"min": 2.7954545454545454,
"max": 28.522727272727273,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1223.0,
"min": 123.0,
"max": 1564.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1696297193",
"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": "1696299009"
},
"total": 1815.3824598639999,
"count": 1,
"self": 0.27640146399971854,
"children": {
"run_training.setup": {
"total": 0.03874328900008095,
"count": 1,
"self": 0.03874328900008095
},
"TrainerController.start_learning": {
"total": 1815.067315111,
"count": 1,
"self": 2.436609245985892,
"children": {
"TrainerController._reset_env": {
"total": 3.972454158000005,
"count": 1,
"self": 3.972454158000005
},
"TrainerController.advance": {
"total": 1808.5276962550142,
"count": 90940,
"self": 1.1766856570352502,
"children": {
"env_step": {
"total": 1807.351010597979,
"count": 90940,
"self": 1326.5876268040247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 479.59847269995396,
"count": 90940,
"self": 6.755478689933852,
"children": {
"TorchPolicy.evaluate": {
"total": 472.8429940100201,
"count": 90940,
"self": 472.8429940100201
}
}
},
"workers": {
"total": 1.1649110940004448,
"count": 90940,
"self": 0.0,
"children": {
"worker_root": {
"total": 1811.6763226980484,
"count": 90940,
"is_parallel": true,
"self": 894.470599284043,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001961008999955993,
"count": 1,
"is_parallel": true,
"self": 0.000590551999721356,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013704570002346372,
"count": 10,
"is_parallel": true,
"self": 0.0013704570002346372
}
}
},
"UnityEnvironment.step": {
"total": 0.03763429900004667,
"count": 1,
"is_parallel": true,
"self": 0.00037869400000545284,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031064500001320994,
"count": 1,
"is_parallel": true,
"self": 0.00031064500001320994
},
"communicator.exchange": {
"total": 0.03488442700006544,
"count": 1,
"is_parallel": true,
"self": 0.03488442700006544
},
"steps_from_proto": {
"total": 0.002060532999962561,
"count": 1,
"is_parallel": true,
"self": 0.00025429500010432093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00180623799985824,
"count": 10,
"is_parallel": true,
"self": 0.00180623799985824
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 917.2057234140053,
"count": 90939,
"is_parallel": true,
"self": 37.15278694606229,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 19.358069107999427,
"count": 90939,
"is_parallel": true,
"self": 19.358069107999427
},
"communicator.exchange": {
"total": 735.7584760650095,
"count": 90939,
"is_parallel": true,
"self": 735.7584760650095
},
"steps_from_proto": {
"total": 124.93639129493408,
"count": 90939,
"is_parallel": true,
"self": 22.58799880781396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.34839248712012,
"count": 909390,
"is_parallel": true,
"self": 102.34839248712012
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00024541900029362296,
"count": 1,
"self": 0.00024541900029362296,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1803.734138635275,
"count": 1056827,
"is_parallel": true,
"self": 17.589348019194404,
"children": {
"process_trajectory": {
"total": 995.0110904000773,
"count": 1056827,
"is_parallel": true,
"self": 991.1343422420782,
"children": {
"RLTrainer._checkpoint": {
"total": 3.8767481579990317,
"count": 20,
"is_parallel": true,
"self": 3.8767481579990317
}
}
},
"_update_policy": {
"total": 791.1337002160034,
"count": 454,
"is_parallel": true,
"self": 219.5194014570128,
"children": {
"TorchPPOOptimizer.update": {
"total": 571.6142987589906,
"count": 23151,
"is_parallel": true,
"self": 571.6142987589906
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1303100329996596,
"count": 1,
"self": 0.000983559999440331,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12932647300021927,
"count": 1,
"self": 0.12932647300021927
}
}
}
}
}
}
}