{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3683750629425049, "min": 1.3683750629425049, "max": 2.8376293182373047, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 13607.1220703125, "min": 13607.1220703125, "max": 30964.2109375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.9808878898620605, "min": 0.4650992155075073, "max": 4.9808878898620605, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 772.0376586914062, "min": 66.97428894042969, "max": 772.0376586914062, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06657513592017852, "min": 0.06320713799719029, "max": 0.07242005251815391, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3328756796008926, "min": 0.25282855198876114, "max": 0.36210026259076955, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.28136027215742593, "min": 0.1324120491866351, "max": 0.34613143754940406, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.4068013607871297, "min": 0.5296481967465404, "max": 1.5052608280789617, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00039361120000000005, "min": 0.00039361120000000005, "max": 0.0066217012, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001968056, "min": 0.001968056, "max": 0.029648456, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 20.12727272727273, "min": 3.522727272727273, "max": 20.12727272727273, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 155.0, "max": 1107.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 20.12727272727273, "min": 3.522727272727273, "max": 20.12727272727273, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 155.0, "max": 1107.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1745051845", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1745052068" }, "total": 223.46877932199993, "count": 1, "self": 0.4355619300000626, "children": { "run_training.setup": { "total": 0.023172071999965738, "count": 1, "self": 0.023172071999965738 }, "TrainerController.start_learning": { "total": 223.0100453199999, "count": 1, "self": 0.19574840899679202, "children": { "TrainerController._reset_env": { "total": 2.800379387000021, "count": 1, "self": 2.800379387000021 }, "TrainerController.advance": { "total": 219.91895609700305, "count": 9096, "self": 0.20650016200193022, "children": { "env_step": { "total": 157.2478731930039, "count": 9096, "self": 119.54125098900772, "children": { "SubprocessEnvManager._take_step": { "total": 37.595088757996905, "count": 9096, "self": 0.6814204389976339, "children": { "TorchPolicy.evaluate": { "total": 36.91366831899927, "count": 9096, "self": 36.91366831899927 } } }, "workers": { "total": 0.11153344599927095, "count": 9096, "self": 0.0, "children": { "worker_root": { "total": 222.18718547499657, "count": 9096, "is_parallel": true, "self": 117.37367632699602, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005937917999972342, "count": 1, "is_parallel": true, "self": 0.004287550999833911, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016503670001384307, "count": 10, "is_parallel": true, "self": 0.0016503670001384307 } } }, "UnityEnvironment.step": { "total": 0.03808987399997932, "count": 1, "is_parallel": true, "self": 0.000594113000033758, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005211339999959819, "count": 1, "is_parallel": true, "self": 0.0005211339999959819 }, "communicator.exchange": { "total": 0.03500839799994537, "count": 1, "is_parallel": true, "self": 0.03500839799994537 }, "steps_from_proto": { "total": 0.001966229000004205, "count": 1, "is_parallel": true, "self": 0.00038514200025474565, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015810869997494592, "count": 10, "is_parallel": true, "self": 0.0015810869997494592 } } } } } } }, "UnityEnvironment.step": { "total": 104.81350914800055, "count": 9095, "is_parallel": true, "self": 4.926319029015531, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7703601019945836, "count": 9095, "is_parallel": true, "self": 2.7703601019945836 }, "communicator.exchange": { "total": 80.92581410199148, "count": 9095, "is_parallel": true, "self": 80.92581410199148 }, "steps_from_proto": { "total": 16.191015914998957, "count": 9095, "is_parallel": true, "self": 2.974234505013783, "children": { "_process_rank_one_or_two_observation": { "total": 13.216781409985174, "count": 90950, "is_parallel": true, "self": 13.216781409985174 } } } } } } } } } } }, "trainer_advance": { "total": 62.46458274199722, "count": 9096, "self": 0.25537200299515916, "children": { "process_trajectory": { "total": 13.927906779002456, "count": 9096, "self": 13.467878151002537, "children": { "RLTrainer._checkpoint": { "total": 0.46002862799991817, "count": 3, "self": 0.46002862799991817 } } }, "_update_policy": { "total": 48.281303959999605, "count": 45, "self": 19.28571329800286, "children": { "TorchPPOOptimizer.update": { "total": 28.995590661996744, "count": 2292, "self": 28.995590661996744 } } } } } } }, "trainer_threads": { "total": 1.0409999049443286e-06, "count": 1, "self": 1.0409999049443286e-06 }, "TrainerController._save_models": { "total": 0.0949603860001389, "count": 1, "self": 0.0009164720001990645, "children": { "RLTrainer._checkpoint": { "total": 0.09404391399993983, "count": 1, "self": 0.09404391399993983 } } } } } } }