{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.260896921157837, "min": 2.260896921157837, "max": 2.8903067111968994, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 21487.564453125, "min": 21487.564453125, "max": 29758.59765625, "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": 2.7147886753082275, "min": 0.10848310589790344, "max": 2.7147886753082275, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 529.3837890625, "min": 21.04572296142578, "max": 529.3837890625, "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": 10.25, "min": 2.8636363636363638, "max": 10.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 451.0, "min": 126.0, "max": 544.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 10.25, "min": 2.8636363636363638, "max": 10.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 451.0, "min": 126.0, "max": 544.0, "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 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.03119076028803344, "min": 0.030324644064724755, "max": 0.03982431573725383, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.03119076028803344, "min": 0.030324644064724755, "max": 0.03982431573725383, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2643603929628929, "min": 0.10406896757582823, "max": 0.2783568767209848, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2643603929628929, "min": 0.10406896757582823, "max": 0.2783568767209848, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.293209235599999e-05, "min": 2.293209235599999e-05, "max": 0.00026924401025199996, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.293209235599999e-05, "min": 2.293209235599999e-05, "max": 0.00026924401025199996, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10764400000000002, "min": 0.10764400000000002, "max": 0.18974799999999997, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10764400000000002, "min": 0.10764400000000002, "max": 0.18974799999999997, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.567559999999996e-05, "min": 8.567559999999996e-05, "max": 0.0008985052, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.567559999999996e-05, "min": 8.567559999999996e-05, "max": 0.0008985052, "count": 9 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710361533", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710361904" }, "total": 371.05637807000016, "count": 1, "self": 0.32254712899998594, "children": { "run_training.setup": { "total": 0.058175157000050604, "count": 1, "self": 0.058175157000050604 }, "TrainerController.start_learning": { "total": 370.6756557840001, "count": 1, "self": 0.4335986389955906, "children": { "TrainerController._reset_env": { "total": 2.9190766350000104, "count": 1, "self": 2.9190766350000104 }, "TrainerController.advance": { "total": 367.2436087220044, "count": 18192, "self": 0.4408980120283559, "children": { "env_step": { "total": 289.1463464069957, "count": 18192, "self": 226.09859325400635, "children": { "SubprocessEnvManager._take_step": { "total": 62.78247694999186, "count": 18192, "self": 1.3891813849954815, "children": { "TorchPolicy.evaluate": { "total": 61.39329556499638, "count": 18192, "self": 61.39329556499638 } } }, "workers": { "total": 0.2652762029974838, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 369.83431145800455, "count": 18192, "is_parallel": true, "self": 173.0308666539902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002532737000137786, "count": 1, "is_parallel": true, "self": 0.0007632859999375796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017694510002002062, "count": 10, "is_parallel": true, "self": 0.0017694510002002062 } } }, "UnityEnvironment.step": { "total": 0.02826898400007849, "count": 1, "is_parallel": true, "self": 0.0005571279998548562, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003967160000684089, "count": 1, "is_parallel": true, "self": 0.0003967160000684089 }, "communicator.exchange": { "total": 0.025833587000079206, "count": 1, "is_parallel": true, "self": 0.025833587000079206 }, "steps_from_proto": { "total": 0.001481553000076019, "count": 1, "is_parallel": true, "self": 0.0003035020001789235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011780509998970956, "count": 10, "is_parallel": true, "self": 0.0011780509998970956 } } } } } } }, "UnityEnvironment.step": { "total": 196.80344480401436, "count": 18191, "is_parallel": true, "self": 7.200884225004529, "children": { "UnityEnvironment._generate_step_input": { "total": 3.8926841530171714, "count": 18191, "is_parallel": true, "self": 3.8926841530171714 }, "communicator.exchange": { "total": 161.70457059099363, "count": 18191, "is_parallel": true, "self": 161.70457059099363 }, "steps_from_proto": { "total": 24.005305834999035, "count": 18191, "is_parallel": true, "self": 4.705077781013415, "children": { "_process_rank_one_or_two_observation": { "total": 19.30022805398562, "count": 181910, "is_parallel": true, "self": 19.30022805398562 } } } } } } } } } } }, "trainer_advance": { "total": 77.65636430298036, "count": 18192, "self": 0.540954147968705, "children": { "process_trajectory": { "total": 25.865606511011265, "count": 18192, "self": 25.446275068011346, "children": { "RLTrainer._checkpoint": { "total": 0.4193314429999191, "count": 4, "self": 0.4193314429999191 } } }, "_update_policy": { "total": 51.249803644000394, "count": 9, "self": 36.293784923995645, "children": { "TorchPPOOptimizer.update": { "total": 14.95601872000475, "count": 1080, "self": 14.95601872000475 } } } } } } }, "trainer_threads": { "total": 9.710001904750243e-07, "count": 1, "self": 9.710001904750243e-07 }, "TrainerController._save_models": { "total": 0.07937081699992632, "count": 1, "self": 0.00047476599979745515, "children": { "RLTrainer._checkpoint": { "total": 0.07889605100012886, "count": 1, "self": 0.07889605100012886 } } } } } } }