XXSg559's picture
First Push
917ed03 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7702776789665222,
"min": 0.7666993737220764,
"max": 2.8587646484375,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7320.71923828125,
"min": 7320.71923828125,
"max": 29182.26953125,
"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": 13.14834976196289,
"min": 0.4453778862953186,
"max": 13.14834976196289,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2563.92822265625,
"min": 86.40331268310547,
"max": 2655.1630859375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06616322824394208,
"min": 0.06437325350273693,
"max": 0.07773322648033225,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2646529129757683,
"min": 0.264248787388936,
"max": 0.38866613240166126,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17927337620480388,
"min": 0.11320690019284466,
"max": 0.29167268802137936,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7170935048192155,
"min": 0.4528276007713786,
"max": 1.4583634401068968,
"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": 25.886363636363637,
"min": 3.1363636363636362,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 138.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.1363636363636362,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 138.0,
"max": 1426.0,
"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": "1743341361",
"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": "1743341787"
},
"total": 426.65713133099985,
"count": 1,
"self": 0.4344806269998571,
"children": {
"run_training.setup": {
"total": 0.03344893700000284,
"count": 1,
"self": 0.03344893700000284
},
"TrainerController.start_learning": {
"total": 426.189201767,
"count": 1,
"self": 0.3488960319855323,
"children": {
"TrainerController._reset_env": {
"total": 3.772894398000062,
"count": 1,
"self": 3.772894398000062
},
"TrainerController.advance": {
"total": 421.9653541020143,
"count": 18192,
"self": 0.35798340802307393,
"children": {
"env_step": {
"total": 295.04731927299144,
"count": 18192,
"self": 223.47232221299123,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.37270485299382,
"count": 18192,
"self": 1.2296682009960023,
"children": {
"TorchPolicy.evaluate": {
"total": 70.14303665199782,
"count": 18192,
"self": 70.14303665199782
}
}
},
"workers": {
"total": 0.20229220700639416,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.75148974801846,
"count": 18192,
"is_parallel": true,
"self": 228.62955586002386,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.01676664699994035,
"count": 1,
"is_parallel": true,
"self": 0.014562984999656692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002203662000283657,
"count": 10,
"is_parallel": true,
"self": 0.002203662000283657
}
}
},
"UnityEnvironment.step": {
"total": 0.04093167799987896,
"count": 1,
"is_parallel": true,
"self": 0.000638266999658299,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003876330001730821,
"count": 1,
"is_parallel": true,
"self": 0.0003876330001730821
},
"communicator.exchange": {
"total": 0.03784954699995069,
"count": 1,
"is_parallel": true,
"self": 0.03784954699995069
},
"steps_from_proto": {
"total": 0.0020562310000968864,
"count": 1,
"is_parallel": true,
"self": 0.00048089400002027105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015753370000766154,
"count": 10,
"is_parallel": true,
"self": 0.0015753370000766154
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 196.1219338879946,
"count": 18191,
"is_parallel": true,
"self": 9.505705071050897,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2769041819808535,
"count": 18191,
"is_parallel": true,
"self": 5.2769041819808535
},
"communicator.exchange": {
"total": 150.8472776639867,
"count": 18191,
"is_parallel": true,
"self": 150.8472776639867
},
"steps_from_proto": {
"total": 30.492046970976162,
"count": 18191,
"is_parallel": true,
"self": 5.422556272998008,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.069490697978154,
"count": 181910,
"is_parallel": true,
"self": 25.069490697978154
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 126.5600514209998,
"count": 18192,
"self": 0.4577028829919527,
"children": {
"process_trajectory": {
"total": 27.26819871900807,
"count": 18192,
"self": 26.733835926007714,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5343627930003549,
"count": 4,
"self": 0.5343627930003549
}
}
},
"_update_policy": {
"total": 98.83414981899978,
"count": 90,
"self": 37.93914486699941,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.89500495200036,
"count": 4587,
"self": 60.89500495200036
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.679999948275508e-07,
"count": 1,
"self": 9.679999948275508e-07
},
"TrainerController._save_models": {
"total": 0.10205626700007997,
"count": 1,
"self": 0.0010948110000299494,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10096145600005002,
"count": 1,
"self": 0.10096145600005002
}
}
}
}
}
}
}