OliP's picture
First version
e88d08c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0295050144195557,
"min": 1.0295050144195557,
"max": 2.868313789367676,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9829.7138671875,
"min": 9829.7138671875,
"max": 29374.40234375,
"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": 12.395588874816895,
"min": 0.43005481362342834,
"max": 12.395588874816895,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2417.139892578125,
"min": 83.43063354492188,
"max": 2505.92041015625,
"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": 0.07162004851567212,
"min": 0.06056319101241088,
"max": 0.07467229728297074,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2864801940626885,
"min": 0.25191280764114454,
"max": 0.37304713303028086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21106671636887625,
"min": 0.12255028277914057,
"max": 0.32581011635415696,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.844266865475505,
"min": 0.49020113111656227,
"max": 1.6290505817707848,
"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": 24.522727272727273,
"min": 3.522727272727273,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 155.0,
"max": 1332.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 3.522727272727273,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 155.0,
"max": 1332.0,
"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": "1674488845",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674489289"
},
"total": 443.43930717,
"count": 1,
"self": 0.3897433350000483,
"children": {
"run_training.setup": {
"total": 0.11319472299999234,
"count": 1,
"self": 0.11319472299999234
},
"TrainerController.start_learning": {
"total": 442.93636911199997,
"count": 1,
"self": 0.5316343579989962,
"children": {
"TrainerController._reset_env": {
"total": 9.765785525999945,
"count": 1,
"self": 9.765785525999945
},
"TrainerController.advance": {
"total": 432.514235052001,
"count": 18202,
"self": 0.2731789189945175,
"children": {
"env_step": {
"total": 432.2410561330065,
"count": 18202,
"self": 280.50743039099507,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.45284155300908,
"count": 18202,
"self": 1.4378806590081012,
"children": {
"TorchPolicy.evaluate": {
"total": 150.01496089400098,
"count": 18202,
"self": 33.36050820399487,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.65445269000611,
"count": 18202,
"self": 116.65445269000611
}
}
}
}
},
"workers": {
"total": 0.280784189002361,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.6744429460048,
"count": 18202,
"is_parallel": true,
"self": 215.4270604789965,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005105963999994856,
"count": 1,
"is_parallel": true,
"self": 0.002618903999973554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024870600000213017,
"count": 10,
"is_parallel": true,
"self": 0.0024870600000213017
}
}
},
"UnityEnvironment.step": {
"total": 0.04656126200006838,
"count": 1,
"is_parallel": true,
"self": 0.0006869070000448119,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003032040000334746,
"count": 1,
"is_parallel": true,
"self": 0.0003032040000334746
},
"communicator.exchange": {
"total": 0.043707730000051015,
"count": 1,
"is_parallel": true,
"self": 0.043707730000051015
},
"steps_from_proto": {
"total": 0.0018634209999390805,
"count": 1,
"is_parallel": true,
"self": 0.0004559300001574229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014074909997816576,
"count": 10,
"is_parallel": true,
"self": 0.0014074909997816576
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.24738246700826,
"count": 18201,
"is_parallel": true,
"self": 8.592435179990616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.179511668020609,
"count": 18201,
"is_parallel": true,
"self": 5.179511668020609
},
"communicator.exchange": {
"total": 180.4192412700021,
"count": 18201,
"is_parallel": true,
"self": 180.4192412700021
},
"steps_from_proto": {
"total": 32.05619434899495,
"count": 18201,
"is_parallel": true,
"self": 6.850946182936923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.205248166058027,
"count": 182010,
"is_parallel": true,
"self": 25.205248166058027
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.57529999948747e-05,
"count": 1,
"self": 4.57529999948747e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 429.2851744870701,
"count": 344155,
"is_parallel": true,
"self": 9.582637759075055,
"children": {
"process_trajectory": {
"total": 245.08467468099445,
"count": 344155,
"is_parallel": true,
"self": 244.33320907499433,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7514656060001244,
"count": 4,
"is_parallel": true,
"self": 0.7514656060001244
}
}
},
"_update_policy": {
"total": 174.61786204700059,
"count": 90,
"is_parallel": true,
"self": 43.62233170500315,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.99553034199744,
"count": 4587,
"is_parallel": true,
"self": 130.99553034199744
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1246684230000028,
"count": 1,
"self": 0.0008405059998040088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1238279170001988,
"count": 1,
"self": 0.1238279170001988
}
}
}
}
}
}
}