mgicraft1937's picture
First Push
c75477e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8858739137649536,
"min": 0.8858739137649536,
"max": 2.8292276859283447,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8419.345703125,
"min": 8419.345703125,
"max": 28880.755859375,
"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": 13.067934036254883,
"min": 0.3941744267940521,
"max": 13.067934036254883,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2548.2470703125,
"min": 76.46984100341797,
"max": 2650.4013671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06763305161696147,
"min": 0.06284079752319183,
"max": 0.07597304240354039,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27053220646784587,
"min": 0.2599246613042173,
"max": 0.37986521201770196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21407371175055412,
"min": 0.13763411236611908,
"max": 0.28402012329475557,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8562948470022165,
"min": 0.5505364494644763,
"max": 1.4201006164737777,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.8636363636363638,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 170.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.8636363636363638,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 170.0,
"max": 1428.0,
"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": "1738561165",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738561590"
},
"total": 425.3715661640001,
"count": 1,
"self": 0.4375412960000631,
"children": {
"run_training.setup": {
"total": 0.028243758999906277,
"count": 1,
"self": 0.028243758999906277
},
"TrainerController.start_learning": {
"total": 424.90578110900015,
"count": 1,
"self": 0.35836261701319927,
"children": {
"TrainerController._reset_env": {
"total": 3.0198225450001246,
"count": 1,
"self": 3.0198225450001246
},
"TrainerController.advance": {
"total": 421.43887840398656,
"count": 18192,
"self": 0.34852116392721655,
"children": {
"env_step": {
"total": 296.235198392033,
"count": 18192,
"self": 224.95013809397688,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.08267984301801,
"count": 18192,
"self": 1.2330744390058044,
"children": {
"TorchPolicy.evaluate": {
"total": 69.84960540401221,
"count": 18192,
"self": 69.84960540401221
}
}
},
"workers": {
"total": 0.20238045503811009,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.3705540869794,
"count": 18192,
"is_parallel": true,
"self": 226.3001974309177,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005603119000170409,
"count": 1,
"is_parallel": true,
"self": 0.003977893999717708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016252250004527014,
"count": 10,
"is_parallel": true,
"self": 0.0016252250004527014
}
}
},
"UnityEnvironment.step": {
"total": 0.03574845000002824,
"count": 1,
"is_parallel": true,
"self": 0.0005709380000098463,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004042890000164334,
"count": 1,
"is_parallel": true,
"self": 0.0004042890000164334
},
"communicator.exchange": {
"total": 0.03288776299996243,
"count": 1,
"is_parallel": true,
"self": 0.03288776299996243
},
"steps_from_proto": {
"total": 0.0018854600000395294,
"count": 1,
"is_parallel": true,
"self": 0.00041885699943122745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001466603000608302,
"count": 10,
"is_parallel": true,
"self": 0.001466603000608302
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.07035665606168,
"count": 18191,
"is_parallel": true,
"self": 9.583125646063763,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.179474333978533,
"count": 18191,
"is_parallel": true,
"self": 5.179474333978533
},
"communicator.exchange": {
"total": 151.69948347800528,
"count": 18191,
"is_parallel": true,
"self": 151.69948347800528
},
"steps_from_proto": {
"total": 30.608273198014103,
"count": 18191,
"is_parallel": true,
"self": 5.339408760945844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.26886443706826,
"count": 181910,
"is_parallel": true,
"self": 25.26886443706826
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.85515884802635,
"count": 18192,
"self": 0.4500807040324162,
"children": {
"process_trajectory": {
"total": 26.80462540399526,
"count": 18192,
"self": 26.25600085599467,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5486245480005891,
"count": 4,
"self": 0.5486245480005891
}
}
},
"_update_policy": {
"total": 97.60045273999867,
"count": 90,
"self": 39.17527822499301,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.425174515005665,
"count": 4587,
"self": 58.425174515005665
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.800002433417831e-07,
"count": 1,
"self": 8.800002433417831e-07
},
"TrainerController._save_models": {
"total": 0.0887166630000138,
"count": 1,
"self": 0.0009478659999331285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08776879700008067,
"count": 1,
"self": 0.08776879700008067
}
}
}
}
}
}
}