TxAA's picture
First Push
3e7e6c2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8226982951164246,
"min": 0.8151152729988098,
"max": 2.8385403156280518,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8470.501953125,
"min": 7818.5859375,
"max": 28975.818359375,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.73716402053833,
"min": 0.2946099042892456,
"max": 2.8057615756988525,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 558.3814697265625,
"min": 57.154319763183594,
"max": 569.9742431640625,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06735629658557145,
"min": 0.06132185949165574,
"max": 0.07102779475806564,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.33678148292785726,
"min": 0.24528743796662297,
"max": 0.3551389737903282,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1151236929729873,
"min": 0.10468905375284307,
"max": 0.15780233004513908,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5756184648649365,
"min": 0.4187562150113723,
"max": 0.7890116502256954,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.2880098237333316e-05,
"min": 5.2880098237333316e-05,
"max": 0.0029458800018039998,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00026440049118666657,
"min": 0.00026440049118666657,
"max": 0.014234400025519999,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10176266666666667,
"min": 0.10176266666666667,
"max": 0.198196,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5088133333333333,
"min": 0.42025066666666666,
"max": 0.97448,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666662e-05,
"min": 9.795706666666662e-05,
"max": 0.0049099804000000006,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0004897853333333331,
"min": 0.0004897853333333331,
"max": 0.023726551999999998,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.745454545454546,
"min": 4.431818181818182,
"max": 27.522727272727273,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1471.0,
"min": 195.0,
"max": 1494.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.745454545454546,
"min": 4.431818181818182,
"max": 27.522727272727273,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1471.0,
"min": 195.0,
"max": 1494.0,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750134366",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750134984"
},
"total": 617.5898268199999,
"count": 1,
"self": 0.4242266400005974,
"children": {
"run_training.setup": {
"total": 0.02051469699927111,
"count": 1,
"self": 0.02051469699927111
},
"TrainerController.start_learning": {
"total": 617.145085483,
"count": 1,
"self": 0.510020779005572,
"children": {
"TrainerController._reset_env": {
"total": 2.645923903000039,
"count": 1,
"self": 2.645923903000039
},
"TrainerController.advance": {
"total": 613.9033552939936,
"count": 27328,
"self": 0.5512030380250508,
"children": {
"env_step": {
"total": 435.2854105390479,
"count": 27328,
"self": 335.42945103009333,
"children": {
"SubprocessEnvManager._take_step": {
"total": 99.54599657300514,
"count": 27328,
"self": 1.7795548820204203,
"children": {
"TorchPolicy.evaluate": {
"total": 97.76644169098472,
"count": 27328,
"self": 97.76644169098472
}
}
},
"workers": {
"total": 0.3099629359494429,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 615.3837970100285,
"count": 27328,
"is_parallel": true,
"self": 320.6325693310464,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019725530000869185,
"count": 1,
"is_parallel": true,
"self": 0.0005746789984186762,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013978740016682423,
"count": 10,
"is_parallel": true,
"self": 0.0013978740016682423
}
}
},
"UnityEnvironment.step": {
"total": 0.05693476099986583,
"count": 1,
"is_parallel": true,
"self": 0.0005850790003023576,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00034602100004121894,
"count": 1,
"is_parallel": true,
"self": 0.00034602100004121894
},
"communicator.exchange": {
"total": 0.054280879999168974,
"count": 1,
"is_parallel": true,
"self": 0.054280879999168974
},
"steps_from_proto": {
"total": 0.0017227810003532795,
"count": 1,
"is_parallel": true,
"self": 0.0003785740018429351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013442069985103444,
"count": 10,
"is_parallel": true,
"self": 0.0013442069985103444
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 294.7512276789821,
"count": 27327,
"is_parallel": true,
"self": 14.211104192042512,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.789133433874667,
"count": 27327,
"is_parallel": true,
"self": 7.789133433874667
},
"communicator.exchange": {
"total": 227.60525451303965,
"count": 27327,
"is_parallel": true,
"self": 227.60525451303965
},
"steps_from_proto": {
"total": 45.14573554002527,
"count": 27327,
"is_parallel": true,
"self": 7.8797047321313585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.26603080789391,
"count": 273270,
"is_parallel": true,
"self": 37.26603080789391
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 178.06674171692066,
"count": 27328,
"self": 0.625410519946854,
"children": {
"process_trajectory": {
"total": 38.640372097965155,
"count": 27328,
"self": 38.03764590196624,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6027261959989119,
"count": 6,
"self": 0.6027261959989119
}
}
},
"_update_policy": {
"total": 138.80095909900865,
"count": 136,
"self": 57.684035995044724,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.11692310396393,
"count": 6933,
"self": 81.11692310396393
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.08578447900072206,
"count": 1,
"self": 0.0011015160007445957,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08468296299997746,
"count": 1,
"self": 0.08468296299997746
}
}
}
}
}
}
}