linqus's picture
First Push
c1b4839
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8767231106758118,
"min": 0.8767231106758118,
"max": 2.863471508026123,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8370.9521484375,
"min": 8370.9521484375,
"max": 29324.8125,
"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": 13.096771240234375,
"min": 0.37227606773376465,
"max": 13.096771240234375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2553.870361328125,
"min": 72.2215576171875,
"max": 2644.73681640625,
"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": 0.06094483769265935,
"min": 0.06094483769265935,
"max": 0.07317894711473034,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2437793507706374,
"min": 0.2437793507706374,
"max": 0.3658947355736517,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18488844308783028,
"min": 0.1279580418257883,
"max": 0.265115867131481,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7395537723513211,
"min": 0.5118321673031532,
"max": 1.3170602792033963,
"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": 25.795454545454547,
"min": 3.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 156.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 3.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 156.0,
"max": 1429.0,
"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": "1701730682",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701731202"
},
"total": 520.381965866,
"count": 1,
"self": 0.43946839599993837,
"children": {
"run_training.setup": {
"total": 0.0625383960000363,
"count": 1,
"self": 0.0625383960000363
},
"TrainerController.start_learning": {
"total": 519.879959074,
"count": 1,
"self": 0.6181291999844234,
"children": {
"TrainerController._reset_env": {
"total": 3.5375498859998515,
"count": 1,
"self": 3.5375498859998515
},
"TrainerController.advance": {
"total": 515.632102532016,
"count": 18198,
"self": 0.306624821015248,
"children": {
"env_step": {
"total": 515.3254777110008,
"count": 18198,
"self": 350.9763250260139,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.03660350899122,
"count": 18198,
"self": 1.586421278979742,
"children": {
"TorchPolicy.evaluate": {
"total": 162.45018223001148,
"count": 18198,
"self": 162.45018223001148
}
}
},
"workers": {
"total": 0.3125491759956276,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 518.4211004070025,
"count": 18198,
"is_parallel": true,
"self": 256.12571866500866,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005675420999978087,
"count": 1,
"is_parallel": true,
"self": 0.004098235000355999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015771859996220883,
"count": 10,
"is_parallel": true,
"self": 0.0015771859996220883
}
}
},
"UnityEnvironment.step": {
"total": 0.06714179200002945,
"count": 1,
"is_parallel": true,
"self": 0.0006660940002802818,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004072939998422953,
"count": 1,
"is_parallel": true,
"self": 0.0004072939998422953
},
"communicator.exchange": {
"total": 0.06402416699984315,
"count": 1,
"is_parallel": true,
"self": 0.06402416699984315
},
"steps_from_proto": {
"total": 0.002044237000063731,
"count": 1,
"is_parallel": true,
"self": 0.0003687600003559055,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016754769997078256,
"count": 10,
"is_parallel": true,
"self": 0.0016754769997078256
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 262.2953817419939,
"count": 18197,
"is_parallel": true,
"self": 11.26354751303279,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.830572408986427,
"count": 18197,
"is_parallel": true,
"self": 5.830572408986427
},
"communicator.exchange": {
"total": 207.20970963798004,
"count": 18197,
"is_parallel": true,
"self": 207.20970963798004
},
"steps_from_proto": {
"total": 37.99155218199462,
"count": 18197,
"is_parallel": true,
"self": 7.19257313403341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.79897904796121,
"count": 181970,
"is_parallel": true,
"self": 30.79897904796121
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001724429998830601,
"count": 1,
"self": 0.0001724429998830601,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 510.9090258599854,
"count": 552770,
"is_parallel": true,
"self": 12.448745152080392,
"children": {
"process_trajectory": {
"total": 289.4176265379035,
"count": 552770,
"is_parallel": true,
"self": 288.5722437979034,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8453827400001046,
"count": 4,
"is_parallel": true,
"self": 0.8453827400001046
}
}
},
"_update_policy": {
"total": 209.04265417000147,
"count": 90,
"is_parallel": true,
"self": 72.09865126800764,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.94400290199383,
"count": 4587,
"is_parallel": true,
"self": 136.94400290199383
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09200501299983443,
"count": 1,
"self": 0.0008978259998002613,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09110718700003417,
"count": 1,
"self": 0.09110718700003417
}
}
}
}
}
}
}