{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8917463421821594, "min": 0.8917463421821594, "max": 2.847630500793457, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8475.1572265625, "min": 8475.1572265625, "max": 29068.61328125, "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": 12.959257125854492, "min": 0.4168141186237335, "max": 12.959257125854492, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2527.05517578125, "min": 80.8619384765625, "max": 2622.09765625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06855017468143498, "min": 0.06181294157931024, "max": 0.07750671496472149, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27420069872573993, "min": 0.24725176631724097, "max": 0.3729600345153206, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19151085191497616, "min": 0.1401153272508607, "max": 0.2695283572755608, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7660434076599046, "min": 0.5604613090034428, "max": 1.3117404168142992, "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": 25.84090909090909, "min": 3.977272727272727, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1137.0, "min": 175.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.84090909090909, "min": 3.977272727272727, "max": 25.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1137.0, "min": 175.0, "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": "1762597529", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1762597960" }, "total": 430.992311085, "count": 1, "self": 0.43324963199938793, "children": { "run_training.setup": { "total": 0.026914325000234385, "count": 1, "self": 0.026914325000234385 }, "TrainerController.start_learning": { "total": 430.53214712800036, "count": 1, "self": 0.3708007290133537, "children": { "TrainerController._reset_env": { "total": 2.9332923900001333, "count": 1, "self": 2.9332923900001333 }, "TrainerController.advance": { "total": 427.152178696987, "count": 18192, "self": 0.36463217305117723, "children": { "env_step": { "total": 308.2063632839727, "count": 18192, "self": 241.78420884102115, "children": { "SubprocessEnvManager._take_step": { "total": 66.20939798598874, "count": 18192, "self": 1.2323239470160843, "children": { "TorchPolicy.evaluate": { "total": 64.97707403897266, "count": 18192, "self": 64.97707403897266 } } }, "workers": { "total": 0.21275645696277934, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 428.82672562603466, "count": 18192, "is_parallel": true, "self": 216.74960127800523, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004403595999974641, "count": 1, "is_parallel": true, "self": 0.0030305329996735964, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013730630003010447, "count": 10, "is_parallel": true, "self": 0.0013730630003010447 } } }, "UnityEnvironment.step": { "total": 0.03521673000022929, "count": 1, "is_parallel": true, "self": 0.0005780869996669935, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003835350003100757, "count": 1, "is_parallel": true, "self": 0.0003835350003100757 }, "communicator.exchange": { "total": 0.03224263099991731, "count": 1, "is_parallel": true, "self": 0.03224263099991731 }, "steps_from_proto": { "total": 0.0020124770003349113, "count": 1, "is_parallel": true, "self": 0.00038491300074383616, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016275639995910751, "count": 10, "is_parallel": true, "self": 0.0016275639995910751 } } } } } } }, "UnityEnvironment.step": { "total": 212.07712434802943, "count": 18191, "is_parallel": true, "self": 9.968271656040542, "children": { "UnityEnvironment._generate_step_input": { "total": 5.258239924983172, "count": 18191, "is_parallel": true, "self": 5.258239924983172 }, "communicator.exchange": { "total": 162.02019685700816, "count": 18191, "is_parallel": true, "self": 162.02019685700816 }, "steps_from_proto": { "total": 34.830415909997555, "count": 18191, "is_parallel": true, "self": 6.356613132811162, "children": { "_process_rank_one_or_two_observation": { "total": 28.473802777186393, "count": 181910, "is_parallel": true, "self": 28.473802777186393 } } } } } } } } } } }, "trainer_advance": { "total": 118.58118323996314, "count": 18192, "self": 0.4476680399357065, "children": { "process_trajectory": { "total": 26.021806842028127, "count": 18192, "self": 25.53106290202777, "children": { "RLTrainer._checkpoint": { "total": 0.4907439400003568, "count": 4, "self": 0.4907439400003568 } } }, "_update_policy": { "total": 92.1117083579993, "count": 90, "self": 38.262650145987664, "children": { "TorchPPOOptimizer.update": { "total": 53.84905821201164, "count": 4587, "self": 53.84905821201164 } } } } } } }, "trainer_threads": { "total": 9.229997885995544e-07, "count": 1, "self": 9.229997885995544e-07 }, "TrainerController._save_models": { "total": 0.07587438900009147, "count": 1, "self": 0.0007051419997878838, "children": { "RLTrainer._checkpoint": { "total": 0.07516924700030359, "count": 1, "self": 0.07516924700030359 } } } } } } }