Logii33's picture
Pushing trained SnowballTarget model
35781c8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9888006448745728,
"min": 0.9694065451622009,
"max": 2.8507471084594727,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9462.822265625,
"min": 9462.822265625,
"max": 29194.5,
"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": 13.041226387023926,
"min": 0.3070796728134155,
"max": 13.041226387023926,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.0390625,
"min": 59.573455810546875,
"max": 2638.26904296875,
"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": 0.06978011968107346,
"min": 0.062636006431835,
"max": 0.07324054579851993,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27912047872429385,
"min": 0.25054402572734,
"max": 0.36620272899259965,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1925367198373173,
"min": 0.12291825775002294,
"max": 0.28512686216363725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7701468793492692,
"min": 0.49167303100009174,
"max": 1.4256343108181861,
"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": 25.772727272727273,
"min": 3.7045454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 163.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.7045454545454546,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 163.0,
"max": 1416.0,
"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": "1723748575",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723749180"
},
"total": 605.4446048220002,
"count": 1,
"self": 0.8424274170001809,
"children": {
"run_training.setup": {
"total": 0.09697117299992897,
"count": 1,
"self": 0.09697117299992897
},
"TrainerController.start_learning": {
"total": 604.5052062320001,
"count": 1,
"self": 0.7421122230202855,
"children": {
"TrainerController._reset_env": {
"total": 2.8744985090002046,
"count": 1,
"self": 2.8744985090002046
},
"TrainerController.advance": {
"total": 600.7105569749792,
"count": 18215,
"self": 0.4117394339527891,
"children": {
"env_step": {
"total": 600.2988175410264,
"count": 18215,
"self": 399.12471170303525,
"children": {
"SubprocessEnvManager._take_step": {
"total": 200.75940706701613,
"count": 18215,
"self": 2.318462026011275,
"children": {
"TorchPolicy.evaluate": {
"total": 198.44094504100485,
"count": 18215,
"self": 198.44094504100485
}
}
},
"workers": {
"total": 0.4146987709750647,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 602.696587991009,
"count": 18215,
"is_parallel": true,
"self": 299.60093726800824,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007508340999720531,
"count": 1,
"is_parallel": true,
"self": 0.0035734609987230215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003934880000997509,
"count": 10,
"is_parallel": true,
"self": 0.003934880000997509
}
}
},
"UnityEnvironment.step": {
"total": 0.04053657499980545,
"count": 1,
"is_parallel": true,
"self": 0.0007175770001595083,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045281699976840173,
"count": 1,
"is_parallel": true,
"self": 0.00045281699976840173
},
"communicator.exchange": {
"total": 0.03720288700014862,
"count": 1,
"is_parallel": true,
"self": 0.03720288700014862
},
"steps_from_proto": {
"total": 0.0021632939997289213,
"count": 1,
"is_parallel": true,
"self": 0.00039266699968720786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017706270000417135,
"count": 10,
"is_parallel": true,
"self": 0.0017706270000417135
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 303.09565072300074,
"count": 18214,
"is_parallel": true,
"self": 13.932817262003937,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.424414621996675,
"count": 18214,
"is_parallel": true,
"self": 7.424414621996675
},
"communicator.exchange": {
"total": 236.39519313997607,
"count": 18214,
"is_parallel": true,
"self": 236.39519313997607
},
"steps_from_proto": {
"total": 45.34322569902406,
"count": 18214,
"is_parallel": true,
"self": 8.764526339950862,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.5786993590732,
"count": 182140,
"is_parallel": true,
"self": 36.5786993590732
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0002111540002260881,
"count": 1,
"self": 0.0002111540002260881,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 592.6077233168608,
"count": 889833,
"is_parallel": true,
"self": 20.426177625871333,
"children": {
"process_trajectory": {
"total": 332.31407108898884,
"count": 889833,
"is_parallel": true,
"self": 330.5635870869887,
"children": {
"RLTrainer._checkpoint": {
"total": 1.750484002000121,
"count": 4,
"is_parallel": true,
"self": 1.750484002000121
}
}
},
"_update_policy": {
"total": 239.86747460200058,
"count": 90,
"is_parallel": true,
"self": 80.82962006896332,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.03785453303726,
"count": 4587,
"is_parallel": true,
"self": 159.03785453303726
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.17782737100014856,
"count": 1,
"self": 0.0015761330005261698,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1762512379996224,
"count": 1,
"self": 0.1762512379996224
}
}
}
}
}
}
}