Jarles's picture
First Push
510d08d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9422165155410767,
"min": 0.9422165155410767,
"max": 2.862046480178833,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8996.283203125,
"min": 8996.283203125,
"max": 29310.21875,
"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": 13.120610237121582,
"min": 0.313411682844162,
"max": 13.14033031463623,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2558.51904296875,
"min": 60.8018684387207,
"max": 2680.0498046875,
"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": 0.06562456289576207,
"min": 0.06396948869252239,
"max": 0.07287958781885476,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2624982515830483,
"min": 0.2624982515830483,
"max": 0.35785580126628025,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19177932540575662,
"min": 0.12699896320198462,
"max": 0.2795647365205428,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7671173016230265,
"min": 0.5079958528079385,
"max": 1.3978236826027142,
"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": 25.84090909090909,
"min": 3.6363636363636362,
"max": 26.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 160.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.6363636363636362,
"max": 26.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 160.0,
"max": 1403.0,
"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": "1707545262",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707545807"
},
"total": 544.545745915,
"count": 1,
"self": 0.5388046130001385,
"children": {
"run_training.setup": {
"total": 0.052899492000051396,
"count": 1,
"self": 0.052899492000051396
},
"TrainerController.start_learning": {
"total": 543.9540418099998,
"count": 1,
"self": 0.8205471739779568,
"children": {
"TrainerController._reset_env": {
"total": 3.763555088999965,
"count": 1,
"self": 3.763555088999965
},
"TrainerController.advance": {
"total": 539.2509897960219,
"count": 18199,
"self": 0.386854514014658,
"children": {
"env_step": {
"total": 538.8641352820073,
"count": 18199,
"self": 353.50691551801265,
"children": {
"SubprocessEnvManager._take_step": {
"total": 184.961273265013,
"count": 18199,
"self": 1.9405443870257386,
"children": {
"TorchPolicy.evaluate": {
"total": 183.02072887798727,
"count": 18199,
"self": 183.02072887798727
}
}
},
"workers": {
"total": 0.3959464989816297,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 542.3322535439909,
"count": 18199,
"is_parallel": true,
"self": 263.18858792199694,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006534483999985241,
"count": 1,
"is_parallel": true,
"self": 0.00439904799964097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021354360003442707,
"count": 10,
"is_parallel": true,
"self": 0.0021354360003442707
}
}
},
"UnityEnvironment.step": {
"total": 0.05999042400003418,
"count": 1,
"is_parallel": true,
"self": 0.0006883570001718908,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004394289999254397,
"count": 1,
"is_parallel": true,
"self": 0.0004394289999254397
},
"communicator.exchange": {
"total": 0.05655724400003237,
"count": 1,
"is_parallel": true,
"self": 0.05655724400003237
},
"steps_from_proto": {
"total": 0.0023053939999044815,
"count": 1,
"is_parallel": true,
"self": 0.00046417199951065413,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018412220003938273,
"count": 10,
"is_parallel": true,
"self": 0.0018412220003938273
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 279.14366562199393,
"count": 18198,
"is_parallel": true,
"self": 12.953516928986573,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.793547909005383,
"count": 18198,
"is_parallel": true,
"self": 6.793547909005383
},
"communicator.exchange": {
"total": 217.70861907000562,
"count": 18198,
"is_parallel": true,
"self": 217.70861907000562
},
"steps_from_proto": {
"total": 41.68798171399635,
"count": 18198,
"is_parallel": true,
"self": 8.116948796998486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.571032916997865,
"count": 181980,
"is_parallel": true,
"self": 33.571032916997865
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001578369999606366,
"count": 1,
"self": 0.0001578369999606366,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 532.0159893899358,
"count": 832434,
"is_parallel": true,
"self": 18.443368217829175,
"children": {
"process_trajectory": {
"total": 297.53030824110624,
"count": 832434,
"is_parallel": true,
"self": 296.9258625531063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6044456879999416,
"count": 4,
"is_parallel": true,
"self": 0.6044456879999416
}
}
},
"_update_policy": {
"total": 216.04231293100042,
"count": 90,
"is_parallel": true,
"self": 60.68489125100473,
"children": {
"TorchPPOOptimizer.update": {
"total": 155.3574216799957,
"count": 4587,
"is_parallel": true,
"self": 155.3574216799957
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1187919139999849,
"count": 1,
"self": 0.0015984359999947628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11719347799999014,
"count": 1,
"self": 0.11719347799999014
}
}
}
}
}
}
}