{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8886215090751648, "min": 0.8464644551277161, "max": 2.851105213165283, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8445.458984375, "min": 8423.416015625, "max": 29104.08203125, "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": 13.217754364013672, "min": 0.2944955825805664, "max": 13.222295761108398, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2577.462158203125, "min": 57.13214111328125, "max": 2697.348388671875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06706198752177514, "min": 0.06409725784090137, "max": 0.0754034922648833, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26824795008710056, "min": 0.25638903136360547, "max": 0.3476245839253762, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19491311695938016, "min": 0.14706109739913076, "max": 0.2950233133984547, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7796524678375206, "min": 0.588244389596523, "max": 1.4751165669922737, "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": 26.068181818181817, "min": 4.113636363636363, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 181.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 4.113636363636363, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 181.0, "max": 1423.0, "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": "1781877949", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781878434" }, "total": 485.16401829100005, "count": 1, "self": 0.47989460400003736, "children": { "run_training.setup": { "total": 0.02550939399998242, "count": 1, "self": 0.02550939399998242 }, "TrainerController.start_learning": { "total": 484.658614293, "count": 1, "self": 0.37659459101223547, "children": { "TrainerController._reset_env": { "total": 2.064814843000022, "count": 1, "self": 2.064814843000022 }, "TrainerController.advance": { "total": 482.12223443998755, "count": 18192, "self": 0.3924938829884468, "children": { "env_step": { "total": 355.7509923480088, "count": 18192, "self": 278.09446524501436, "children": { "SubprocessEnvManager._take_step": { "total": 77.42524438999226, "count": 18192, "self": 1.3574248530007935, "children": { "TorchPolicy.evaluate": { "total": 76.06781953699146, "count": 18192, "self": 76.06781953699146 } } }, "workers": { "total": 0.2312827130022015, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 482.66562777300123, "count": 18192, "is_parallel": true, "self": 238.11739770100144, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001962091999985205, "count": 1, "is_parallel": true, "self": 0.0006129629994120478, "children": { "_process_rank_one_or_two_observation": { "total": 0.001349129000573157, "count": 10, "is_parallel": true, "self": 0.001349129000573157 } } }, "UnityEnvironment.step": { "total": 0.03964018200008468, "count": 1, "is_parallel": true, "self": 0.0006174460002057458, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004351840000254015, "count": 1, "is_parallel": true, "self": 0.0004351840000254015 }, "communicator.exchange": { "total": 0.03658668499997475, "count": 1, "is_parallel": true, "self": 0.03658668499997475 }, "steps_from_proto": { "total": 0.002000866999878781, "count": 1, "is_parallel": true, "self": 0.0003497910001897253, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016510759996890556, "count": 10, "is_parallel": true, "self": 0.0016510759996890556 } } } } } } }, "UnityEnvironment.step": { "total": 244.5482300719998, "count": 18191, "is_parallel": true, "self": 10.99402476801265, "children": { "UnityEnvironment._generate_step_input": { "total": 5.956338888990558, "count": 18191, "is_parallel": true, "self": 5.956338888990558 }, "communicator.exchange": { "total": 186.9635543789891, "count": 18191, "is_parallel": true, "self": 186.9635543789891 }, "steps_from_proto": { "total": 40.634312036007486, "count": 18191, "is_parallel": true, "self": 7.010366296992743, "children": { "_process_rank_one_or_two_observation": { "total": 33.623945739014744, "count": 181910, "is_parallel": true, "self": 33.623945739014744 } } } } } } } } } } }, "trainer_advance": { "total": 125.97874820899028, "count": 18192, "self": 0.4626488769952175, "children": { "process_trajectory": { "total": 26.246688990995153, "count": 18192, "self": 25.819520030995363, "children": { "RLTrainer._checkpoint": { "total": 0.4271689599997899, "count": 4, "self": 0.4271689599997899 } } }, "_update_policy": { "total": 99.26941034099991, "count": 90, "self": 40.00246495600345, "children": { "TorchPPOOptimizer.update": { "total": 59.26694538499646, "count": 4587, "self": 59.26694538499646 } } } } } } }, "trainer_threads": { "total": 1.2000000424450263e-06, "count": 1, "self": 1.2000000424450263e-06 }, "TrainerController._save_models": { "total": 0.09496921900017696, "count": 1, "self": 0.000991740000245045, "children": { "RLTrainer._checkpoint": { "total": 0.09397747899993192, "count": 1, "self": 0.09397747899993192 } } } } } } }