timtaotao's picture
snowball
bbace80
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2258657217025757,
"min": 1.2258657217025757,
"max": 2.8513195514678955,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11745.01953125,
"min": 11745.01953125,
"max": 29200.36328125,
"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": 11.306317329406738,
"min": 0.3119215965270996,
"max": 11.306317329406738,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2204.73193359375,
"min": 60.512786865234375,
"max": 2256.69970703125,
"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": 0.07412744486239664,
"min": 0.0656778153842977,
"max": 0.07412744486239664,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29650977944958656,
"min": 0.2627112615371908,
"max": 0.36772987429810433,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20323434662000806,
"min": 0.12610914078130223,
"max": 0.29673037353683923,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8129373864800322,
"min": 0.5044365631252089,
"max": 1.483651867684196,
"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": 22.522727272727273,
"min": 3.3636363636363638,
"max": 22.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 991.0,
"min": 148.0,
"max": 1224.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.522727272727273,
"min": 3.3636363636363638,
"max": 22.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 991.0,
"min": 148.0,
"max": 1224.0,
"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": "1679909760",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679910211"
},
"total": 450.952626711,
"count": 1,
"self": 0.7880230190003203,
"children": {
"run_training.setup": {
"total": 0.10654219199977888,
"count": 1,
"self": 0.10654219199977888
},
"TrainerController.start_learning": {
"total": 450.0580614999999,
"count": 1,
"self": 0.5002550779963713,
"children": {
"TrainerController._reset_env": {
"total": 9.114389490000121,
"count": 1,
"self": 9.114389490000121
},
"TrainerController.advance": {
"total": 440.2374267570035,
"count": 18218,
"self": 0.25064901700579867,
"children": {
"env_step": {
"total": 439.9867777399977,
"count": 18218,
"self": 318.20759321296623,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.52354119901293,
"count": 18218,
"self": 2.0059441779940244,
"children": {
"TorchPolicy.evaluate": {
"total": 119.5175970210189,
"count": 18218,
"self": 119.5175970210189
}
}
},
"workers": {
"total": 0.25564332801855016,
"count": 18218,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.61047182800235,
"count": 18218,
"is_parallel": true,
"self": 215.16681821399607,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005563633999827289,
"count": 1,
"is_parallel": true,
"self": 0.003927516999738145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016361170000891434,
"count": 10,
"is_parallel": true,
"self": 0.0016361170000891434
}
}
},
"UnityEnvironment.step": {
"total": 0.05652169200016033,
"count": 1,
"is_parallel": true,
"self": 0.00040639700046085636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035265899987280136,
"count": 1,
"is_parallel": true,
"self": 0.00035265899987280136
},
"communicator.exchange": {
"total": 0.05404113399981725,
"count": 1,
"is_parallel": true,
"self": 0.05404113399981725
},
"steps_from_proto": {
"total": 0.0017215020000094228,
"count": 1,
"is_parallel": true,
"self": 0.00035410399982538365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013673980001840391,
"count": 10,
"is_parallel": true,
"self": 0.0013673980001840391
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.44365361400628,
"count": 18217,
"is_parallel": true,
"self": 9.190842824975562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.92253293001022,
"count": 18217,
"is_parallel": true,
"self": 4.92253293001022
},
"communicator.exchange": {
"total": 189.5116560580136,
"count": 18217,
"is_parallel": true,
"self": 189.5116560580136
},
"steps_from_proto": {
"total": 29.818621801006884,
"count": 18217,
"is_parallel": true,
"self": 5.793242739955986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.0253790610509,
"count": 182170,
"is_parallel": true,
"self": 24.0253790610509
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001362119999157585,
"count": 1,
"self": 0.0001362119999157585,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 436.9857611730456,
"count": 385612,
"is_parallel": true,
"self": 9.332194299149023,
"children": {
"process_trajectory": {
"total": 242.31276269289629,
"count": 385612,
"is_parallel": true,
"self": 240.78366218889641,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5291005039998709,
"count": 4,
"is_parallel": true,
"self": 1.5291005039998709
}
}
},
"_update_policy": {
"total": 185.3408041810003,
"count": 90,
"is_parallel": true,
"self": 68.8382885209976,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.5025156600027,
"count": 4587,
"is_parallel": true,
"self": 116.5025156600027
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.20585396299998138,
"count": 1,
"self": 0.0011526060000051075,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20470135699997627,
"count": 1,
"self": 0.20470135699997627
}
}
}
}
}
}
}