guirnd's picture
First Push
ea93dce verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8236265778541565,
"min": 0.8205353617668152,
"max": 2.856825590133667,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7873.04638671875,
"min": 7873.04638671875,
"max": 29256.751953125,
"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": 12.49542236328125,
"min": 0.255828320980072,
"max": 12.49542236328125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2436.607421875,
"min": 49.63069534301758,
"max": 2519.0654296875,
"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": 0.06903686689831517,
"min": 0.06442571627506849,
"max": 0.07442553017982373,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2761474675932607,
"min": 0.25770286510027396,
"max": 0.37212765089911864,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2216127905629429,
"min": 0.11950748383213639,
"max": 0.2864517402269092,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8864511622517716,
"min": 0.47802993532854554,
"max": 1.3455725262562432,
"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": 24.613636363636363,
"min": 3.1363636363636362,
"max": 24.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 138.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.1363636363636362,
"max": 24.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 138.0,
"max": 1359.0,
"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": "1706899127",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706899549"
},
"total": 422.366725503,
"count": 1,
"self": 0.4314688859999478,
"children": {
"run_training.setup": {
"total": 0.060158885000078044,
"count": 1,
"self": 0.060158885000078044
},
"TrainerController.start_learning": {
"total": 421.875097732,
"count": 1,
"self": 0.5209304159923249,
"children": {
"TrainerController._reset_env": {
"total": 3.584521010000003,
"count": 1,
"self": 3.584521010000003
},
"TrainerController.advance": {
"total": 417.67618030400763,
"count": 18199,
"self": 0.25277981700196506,
"children": {
"env_step": {
"total": 417.42340048700567,
"count": 18199,
"self": 267.66940331600006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.4875825300046,
"count": 18199,
"self": 1.390089516009425,
"children": {
"TorchPolicy.evaluate": {
"total": 148.09749301399518,
"count": 18199,
"self": 148.09749301399518
}
}
},
"workers": {
"total": 0.2664146410010062,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.77899495799966,
"count": 18199,
"is_parallel": true,
"self": 210.53210362699758,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005013254000004963,
"count": 1,
"is_parallel": true,
"self": 0.0034337920000098165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015794619999951465,
"count": 10,
"is_parallel": true,
"self": 0.0015794619999951465
}
}
},
"UnityEnvironment.step": {
"total": 0.03639974899999743,
"count": 1,
"is_parallel": true,
"self": 0.000618328999962614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039751600002091436,
"count": 1,
"is_parallel": true,
"self": 0.00039751600002091436
},
"communicator.exchange": {
"total": 0.033523413000011715,
"count": 1,
"is_parallel": true,
"self": 0.033523413000011715
},
"steps_from_proto": {
"total": 0.0018604910000021846,
"count": 1,
"is_parallel": true,
"self": 0.0003730570000470834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014874339999551012,
"count": 10,
"is_parallel": true,
"self": 0.0014874339999551012
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.24689133100208,
"count": 18198,
"is_parallel": true,
"self": 10.305579154008115,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.168357937001133,
"count": 18198,
"is_parallel": true,
"self": 5.168357937001133
},
"communicator.exchange": {
"total": 162.8395410179919,
"count": 18198,
"is_parallel": true,
"self": 162.8395410179919
},
"steps_from_proto": {
"total": 31.933413222000922,
"count": 18198,
"is_parallel": true,
"self": 5.785197038060915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.148216183940008,
"count": 181980,
"is_parallel": true,
"self": 26.148216183940008
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011982700016233139,
"count": 1,
"self": 0.00011982700016233139,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 412.2749093390173,
"count": 652714,
"is_parallel": true,
"self": 13.530716034036118,
"children": {
"process_trajectory": {
"total": 227.3427327759805,
"count": 652714,
"is_parallel": true,
"self": 226.84362848698038,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4991042890001154,
"count": 4,
"is_parallel": true,
"self": 0.4991042890001154
}
}
},
"_update_policy": {
"total": 171.4014605290007,
"count": 90,
"is_parallel": true,
"self": 49.1462508780005,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.2552096510002,
"count": 4587,
"is_parallel": true,
"self": 122.2552096510002
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09334617499985143,
"count": 1,
"self": 0.000985886999842478,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09236028800000895,
"count": 1,
"self": 0.09236028800000895
}
}
}
}
}
}
}