jokyere49's picture
using default params
72ccda4
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9804554581642151,
"min": 0.9804554581642151,
"max": 2.863400936126709,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9372.173828125,
"min": 9372.173828125,
"max": 29292.591796875,
"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": 13.120930671691895,
"min": 0.4205845594406128,
"max": 13.120930671691895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2558.58154296875,
"min": 81.5934066772461,
"max": 2648.2587890625,
"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": 0.07279006477320389,
"min": 0.06292881680408255,
"max": 0.07579981144369288,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29116025909281557,
"min": 0.2567565574144657,
"max": 0.3789990572184644,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18673850376816356,
"min": 0.13454334263680687,
"max": 0.27251439854210496,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7469540150726542,
"min": 0.5381733705472275,
"max": 1.3625719927105249,
"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": 26.386363636363637,
"min": 3.522727272727273,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1161.0,
"min": 155.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.386363636363637,
"min": 3.522727272727273,
"max": 26.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1161.0,
"min": 155.0,
"max": 1394.0,
"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": "1684680282",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "1684680757"
},
"total": 475.1683493119999,
"count": 1,
"self": 0.7931769289998556,
"children": {
"run_training.setup": {
"total": 0.04862926400005563,
"count": 1,
"self": 0.04862926400005563
},
"TrainerController.start_learning": {
"total": 474.326543119,
"count": 1,
"self": 0.5490942650096713,
"children": {
"TrainerController._reset_env": {
"total": 4.090084889999844,
"count": 1,
"self": 4.090084889999844
},
"TrainerController.advance": {
"total": 469.4535087759905,
"count": 18220,
"self": 0.2611201119884754,
"children": {
"env_step": {
"total": 469.192388664002,
"count": 18220,
"self": 342.4732193729749,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.4530450510274,
"count": 18220,
"self": 1.9482150880282916,
"children": {
"TorchPolicy.evaluate": {
"total": 124.50482996299911,
"count": 18220,
"self": 124.50482996299911
}
}
},
"workers": {
"total": 0.26612423999972634,
"count": 18220,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.65041676399846,
"count": 18220,
"is_parallel": true,
"self": 224.33415623299175,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005879489000108151,
"count": 1,
"is_parallel": true,
"self": 0.004189603999748215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016898850003599364,
"count": 10,
"is_parallel": true,
"self": 0.0016898850003599364
}
}
},
"UnityEnvironment.step": {
"total": 0.04238773800011586,
"count": 1,
"is_parallel": true,
"self": 0.004524816999719405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003624620001119183,
"count": 1,
"is_parallel": true,
"self": 0.0003624620001119183
},
"communicator.exchange": {
"total": 0.03515627700016921,
"count": 1,
"is_parallel": true,
"self": 0.03515627700016921
},
"steps_from_proto": {
"total": 0.0023441820001153246,
"count": 1,
"is_parallel": true,
"self": 0.0004956390000643296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001848543000050995,
"count": 10,
"is_parallel": true,
"self": 0.001848543000050995
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.31626053100672,
"count": 18219,
"is_parallel": true,
"self": 10.144084827025608,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.431058823999365,
"count": 18219,
"is_parallel": true,
"self": 5.431058823999365
},
"communicator.exchange": {
"total": 198.49665900000787,
"count": 18219,
"is_parallel": true,
"self": 198.49665900000787
},
"steps_from_proto": {
"total": 34.24445787997388,
"count": 18219,
"is_parallel": true,
"self": 6.630636815989192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.613821063984687,
"count": 182190,
"is_parallel": true,
"self": 27.613821063984687
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014774800001760013,
"count": 1,
"self": 0.00014774800001760013,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 465.78479506497547,
"count": 431581,
"is_parallel": true,
"self": 10.092097662999095,
"children": {
"process_trajectory": {
"total": 253.59856975397656,
"count": 431581,
"is_parallel": true,
"self": 251.91690215897665,
"children": {
"RLTrainer._checkpoint": {
"total": 1.681667594999908,
"count": 4,
"is_parallel": true,
"self": 1.681667594999908
}
}
},
"_update_policy": {
"total": 202.0941276479998,
"count": 90,
"is_parallel": true,
"self": 79.1462782849951,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.9478493630047,
"count": 4587,
"is_parallel": true,
"self": 122.9478493630047
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23370743999998922,
"count": 1,
"self": 0.001114958000016486,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23259248199997273,
"count": 1,
"self": 0.23259248199997273
}
}
}
}
}
}
}