DiurD's picture
First Push
5aacdaf verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7940777540206909,
"min": 0.7940777540206909,
"max": 2.871960401535034,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7546.9150390625,
"min": 7546.9150390625,
"max": 29316.970703125,
"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": 13.067039489746094,
"min": 0.22978009283542633,
"max": 13.067039489746094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.07275390625,
"min": 44.57733917236328,
"max": 2642.239013671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07350377395385865,
"min": 0.060483353554017794,
"max": 0.0799842310042746,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2940150958154346,
"min": 0.24193341421607117,
"max": 0.36105178896333184,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20055020271855242,
"min": 0.10003234343899998,
"max": 0.30681699463257606,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8022008108742097,
"min": 0.40012937375599994,
"max": 1.4052221193617465,
"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.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": 26.068181818181817,
"min": 2.7954545454545454,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 123.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 2.7954545454545454,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 123.0,
"max": 1399.0,
"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": "1739224200",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739224649"
},
"total": 449.0019720700002,
"count": 1,
"self": 0.48493170100005045,
"children": {
"run_training.setup": {
"total": 0.02397429600000578,
"count": 1,
"self": 0.02397429600000578
},
"TrainerController.start_learning": {
"total": 448.49306607300014,
"count": 1,
"self": 0.3315470290185658,
"children": {
"TrainerController._reset_env": {
"total": 2.020537930000046,
"count": 1,
"self": 2.020537930000046
},
"TrainerController.advance": {
"total": 446.0514895569818,
"count": 18192,
"self": 0.3598172339679877,
"children": {
"env_step": {
"total": 314.0534118279945,
"count": 18192,
"self": 240.36542321201705,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.484211104005,
"count": 18192,
"self": 1.2673259249950206,
"children": {
"TorchPolicy.evaluate": {
"total": 72.21688517900998,
"count": 18192,
"self": 72.21688517900998
}
}
},
"workers": {
"total": 0.20377751197247562,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.7480973179704,
"count": 18192,
"is_parallel": true,
"self": 235.9108544009655,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002077949000067747,
"count": 1,
"is_parallel": true,
"self": 0.0006870570005048648,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013908919995628821,
"count": 10,
"is_parallel": true,
"self": 0.0013908919995628821
}
}
},
"UnityEnvironment.step": {
"total": 0.03468362100011291,
"count": 1,
"is_parallel": true,
"self": 0.0005491890003668232,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003783679999287415,
"count": 1,
"is_parallel": true,
"self": 0.0003783679999287415
},
"communicator.exchange": {
"total": 0.031868320999819844,
"count": 1,
"is_parallel": true,
"self": 0.031868320999819844
},
"steps_from_proto": {
"total": 0.0018877429999974993,
"count": 1,
"is_parallel": true,
"self": 0.00035548099981497217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015322620001825271,
"count": 10,
"is_parallel": true,
"self": 0.0015322620001825271
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.83724291700491,
"count": 18191,
"is_parallel": true,
"self": 9.891301844004602,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.45705523599554,
"count": 18191,
"is_parallel": true,
"self": 5.45705523599554
},
"communicator.exchange": {
"total": 163.2173274930176,
"count": 18191,
"is_parallel": true,
"self": 163.2173274930176
},
"steps_from_proto": {
"total": 32.27155834398718,
"count": 18191,
"is_parallel": true,
"self": 5.768710755082111,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.50284758890507,
"count": 181910,
"is_parallel": true,
"self": 26.50284758890507
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.63826049501927,
"count": 18192,
"self": 0.41530651502102955,
"children": {
"process_trajectory": {
"total": 28.357611578998103,
"count": 18192,
"self": 27.723474547998194,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6341370309999093,
"count": 4,
"self": 0.6341370309999093
}
}
},
"_update_policy": {
"total": 102.86534240100013,
"count": 90,
"self": 42.41716447300473,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.4481779279954,
"count": 4587,
"self": 60.4481779279954
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.746999714669073e-06,
"count": 1,
"self": 1.746999714669073e-06
},
"TrainerController._save_models": {
"total": 0.08948981000003187,
"count": 1,
"self": 0.0011854590002258192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08830435099980605,
"count": 1,
"self": 0.08830435099980605
}
}
}
}
}
}
}