{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6637901067733765, "min": 0.6637901067733765, "max": 2.868617296218872, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6308.6611328125, "min": 6308.6611328125, "max": 29282.845703125, "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": 13.00213623046875, "min": 0.22362938523292542, "max": 13.00213623046875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.41650390625, "min": 43.38410186767578, "max": 2630.990234375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06490169358035999, "min": 0.06169103981147048, "max": 0.0759720364886829, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25960677432143997, "min": 0.2467641592458819, "max": 0.3798601824434145, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20159022122913717, "min": 0.09974760613655306, "max": 0.294673148206636, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8063608849165487, "min": 0.39899042454621225, "max": 1.47336574103318, "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": 25.5, "min": 2.8181818181818183, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1122.0, "min": 124.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.5, "min": 2.8181818181818183, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1122.0, "min": 124.0, "max": 1407.0, "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": "1783024231", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1783025012" }, "total": 781.1094181970002, "count": 1, "self": 1.0077948580010343, "children": { "run_training.setup": { "total": 0.07508707599936315, "count": 1, "self": 0.07508707599936315 }, "TrainerController.start_learning": { "total": 780.0265362629998, "count": 1, "self": 0.5993564480586429, "children": { "TrainerController._reset_env": { "total": 3.1641971710005237, "count": 1, "self": 3.1641971710005237 }, "TrainerController.advance": { "total": 776.1401747229402, "count": 18192, "self": 0.5426467248471454, "children": { "env_step": { "total": 585.5073013620331, "count": 18192, "self": 482.6799854431156, "children": { "SubprocessEnvManager._take_step": { "total": 102.5145659509626, "count": 18192, "self": 1.8301177749281123, "children": { "TorchPolicy.evaluate": { "total": 100.6844481760345, "count": 18192, "self": 100.6844481760345 } } }, "workers": { "total": 0.3127499679549146, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 773.4744462541075, "count": 18192, "is_parallel": true, "self": 348.7597558611924, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030379059999177116, "count": 1, "is_parallel": true, "self": 0.0007762840004943428, "children": { "_process_rank_one_or_two_observation": { "total": 0.002261621999423369, "count": 10, "is_parallel": true, "self": 0.002261621999423369 } } }, "UnityEnvironment.step": { "total": 0.0681476850004401, "count": 1, "is_parallel": true, "self": 0.0005914710000070045, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003753849996428471, "count": 1, "is_parallel": true, "self": 0.0003753849996428471 }, "communicator.exchange": { "total": 0.06316776800031221, "count": 1, "is_parallel": true, "self": 0.06316776800031221 }, "steps_from_proto": { "total": 0.0040130610004780465, "count": 1, "is_parallel": true, "self": 0.0004270270010238164, "children": { "_process_rank_one_or_two_observation": { "total": 0.00358603399945423, "count": 10, "is_parallel": true, "self": 0.00358603399945423 } } } } } } }, "UnityEnvironment.step": { "total": 424.71469039291514, "count": 18191, "is_parallel": true, "self": 12.404453058036779, "children": { "UnityEnvironment._generate_step_input": { "total": 5.698063156921307, "count": 18191, "is_parallel": true, "self": 5.698063156921307 }, "communicator.exchange": { "total": 337.8958448980029, "count": 18191, "is_parallel": true, "self": 337.8958448980029 }, "steps_from_proto": { "total": 68.71632927995415, "count": 18191, "is_parallel": true, "self": 12.651767452993226, "children": { "_process_rank_one_or_two_observation": { "total": 56.064561826960926, "count": 181910, "is_parallel": true, "self": 56.064561826960926 } } } } } } } } } } }, "trainer_advance": { "total": 190.09022663605992, "count": 18192, "self": 0.6566085130007195, "children": { "process_trajectory": { "total": 38.172711078060274, "count": 18192, "self": 37.59512009605987, "children": { "RLTrainer._checkpoint": { "total": 0.5775909820004017, "count": 4, "self": 0.5775909820004017 } } }, "_update_policy": { "total": 151.26090704499893, "count": 90, "self": 72.41980554298789, "children": { "TorchPPOOptimizer.update": { "total": 78.84110150201104, "count": 4587, "self": 78.84110150201104 } } } } } } }, "trainer_threads": { "total": 1.2480004443204962e-06, "count": 1, "self": 1.2480004443204962e-06 }, "TrainerController._save_models": { "total": 0.12280667300001369, "count": 1, "self": 0.0016504940003869706, "children": { "RLTrainer._checkpoint": { "total": 0.12115617899962672, "count": 1, "self": 0.12115617899962672 } } } } } } }