hossniper's picture
First Push
12e522e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.020825982093811,
"min": 1.020825982093811,
"max": 2.8602981567382812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9780.533203125,
"min": 9780.533203125,
"max": 29355.240234375,
"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": 11.559516906738281,
"min": 0.237765833735466,
"max": 11.559516906738281,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2254.105712890625,
"min": 46.12657165527344,
"max": 2321.322265625,
"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": 0.06566507372447043,
"min": 0.062066744375453495,
"max": 0.07609850286811992,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26266029489788173,
"min": 0.2517676772435616,
"max": 0.3567125645772025,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18301341244403055,
"min": 0.11874786808324393,
"max": 0.26643419803357593,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7320536497761222,
"min": 0.47499147233297573,
"max": 1.3321709901678798,
"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": 22.772727272727273,
"min": 3.159090909090909,
"max": 23.054545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1002.0,
"min": 139.0,
"max": 1268.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.772727272727273,
"min": 3.159090909090909,
"max": 23.054545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1002.0,
"min": 139.0,
"max": 1268.0,
"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": "1714195345",
"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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714195723"
},
"total": 377.9898403320003,
"count": 1,
"self": 0.32178669100085244,
"children": {
"run_training.setup": {
"total": 0.05103682099979778,
"count": 1,
"self": 0.05103682099979778
},
"TrainerController.start_learning": {
"total": 377.61701681999966,
"count": 1,
"self": 0.4979166989924124,
"children": {
"TrainerController._reset_env": {
"total": 2.641631729999972,
"count": 1,
"self": 2.641631729999972
},
"TrainerController.advance": {
"total": 374.39175074100694,
"count": 18202,
"self": 0.22480279602132214,
"children": {
"env_step": {
"total": 374.1669479449856,
"count": 18202,
"self": 255.07010325994725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.87162501104012,
"count": 18202,
"self": 1.2156723400175906,
"children": {
"TorchPolicy.evaluate": {
"total": 117.65595267102253,
"count": 18202,
"self": 117.65595267102253
}
}
},
"workers": {
"total": 0.2252196739982537,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 376.97106310493837,
"count": 18202,
"is_parallel": true,
"self": 189.7791371429903,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024458580001009977,
"count": 1,
"is_parallel": true,
"self": 0.0006822710001870291,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017635869999139686,
"count": 10,
"is_parallel": true,
"self": 0.0017635869999139686
}
}
},
"UnityEnvironment.step": {
"total": 0.027688830999977654,
"count": 1,
"is_parallel": true,
"self": 0.0004392179998831125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028198499967402313,
"count": 1,
"is_parallel": true,
"self": 0.00028198499967402313
},
"communicator.exchange": {
"total": 0.025667614000667527,
"count": 1,
"is_parallel": true,
"self": 0.025667614000667527
},
"steps_from_proto": {
"total": 0.0013000139997529914,
"count": 1,
"is_parallel": true,
"self": 0.00025843200091912877,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010415819988338626,
"count": 10,
"is_parallel": true,
"self": 0.0010415819988338626
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 187.19192596194807,
"count": 18201,
"is_parallel": true,
"self": 6.965864129972033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.705910725972899,
"count": 18201,
"is_parallel": true,
"self": 3.705910725972899
},
"communicator.exchange": {
"total": 153.69084111302163,
"count": 18201,
"is_parallel": true,
"self": 153.69084111302163
},
"steps_from_proto": {
"total": 22.829309992981507,
"count": 18201,
"is_parallel": true,
"self": 4.466689484241215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.362620508740292,
"count": 182010,
"is_parallel": true,
"self": 18.362620508740292
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016121800035762135,
"count": 1,
"self": 0.00016121800035762135,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 373.5196023542321,
"count": 235850,
"is_parallel": true,
"self": 3.1970469013431284,
"children": {
"process_trajectory": {
"total": 211.79600217489224,
"count": 235850,
"is_parallel": true,
"self": 211.21951668989186,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5764854850003758,
"count": 4,
"is_parallel": true,
"self": 0.5764854850003758
}
}
},
"_update_policy": {
"total": 158.52655327799675,
"count": 90,
"is_parallel": true,
"self": 36.317345643976296,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.20920763402046,
"count": 4587,
"is_parallel": true,
"self": 122.20920763402046
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08555643199997576,
"count": 1,
"self": 0.0009363899998788838,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08462004200009687,
"count": 1,
"self": 0.08462004200009687
}
}
}
}
}
}
}