{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8749719858169556, "min": 0.8749719858169556, "max": 2.869377851486206, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8363.857421875, "min": 8363.857421875, "max": 29385.298828125, "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": 12.858697891235352, "min": 0.10764481127262115, "max": 12.858697891235352, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2507.446044921875, "min": 20.883092880249023, "max": 2609.34619140625, "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.Losses.PolicyLoss.mean": { "value": 0.06836821630442465, "min": 0.061049089995132956, "max": 0.07396343235821262, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2734728652176986, "min": 0.25839918297581377, "max": 0.3612354066104208, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19780479966863698, "min": 0.09011861768793132, "max": 0.28889068406002194, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7912191986745479, "min": 0.3604744707517253, "max": 1.4444534203001096, "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.CumulativeReward.mean": { "value": 25.522727272727273, "min": 2.522727272727273, "max": 25.69090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 111.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 2.522727272727273, "max": 25.69090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 111.0, "max": 1413.0, "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": "1724370300", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724370752" }, "total": 452.10824516599996, "count": 1, "self": 0.4367869359998622, "children": { "run_training.setup": { "total": 0.06039139699998941, "count": 1, "self": 0.06039139699998941 }, "TrainerController.start_learning": { "total": 451.6110668330001, "count": 1, "self": 0.6122902739980418, "children": { "TrainerController._reset_env": { "total": 2.9953696979999904, "count": 1, "self": 2.9953696979999904 }, "TrainerController.advance": { "total": 447.9163333690019, "count": 18202, "self": 0.2826264700033789, "children": { "env_step": { "total": 447.6337068989985, "count": 18202, "self": 290.0868200190014, "children": { "SubprocessEnvManager._take_step": { "total": 157.23906080999757, "count": 18202, "self": 1.4816981799938276, "children": { "TorchPolicy.evaluate": { "total": 155.75736263000374, "count": 18202, "self": 155.75736263000374 } } }, "workers": { "total": 0.30782606999957807, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 450.35650475599414, "count": 18202, "is_parallel": true, "self": 227.80986744498887, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004954196999960914, "count": 1, "is_parallel": true, "self": 0.0033022230003325603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016519739996283533, "count": 10, "is_parallel": true, "self": 0.0016519739996283533 } } }, "UnityEnvironment.step": { "total": 0.03598834199999601, "count": 1, "is_parallel": true, "self": 0.0008562829999618771, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039715900004466675, "count": 1, "is_parallel": true, "self": 0.00039715900004466675 }, "communicator.exchange": { "total": 0.0328182599999991, "count": 1, "is_parallel": true, "self": 0.0328182599999991 }, "steps_from_proto": { "total": 0.001916639999990366, "count": 1, "is_parallel": true, "self": 0.0003628400000934562, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015537999998969099, "count": 10, "is_parallel": true, "self": 0.0015537999998969099 } } } } } } }, "UnityEnvironment.step": { "total": 222.54663731100527, "count": 18201, "is_parallel": true, "self": 10.135452454007691, "children": { "UnityEnvironment._generate_step_input": { "total": 5.271669187005955, "count": 18201, "is_parallel": true, "self": 5.271669187005955 }, "communicator.exchange": { "total": 174.2150602320071, "count": 18201, "is_parallel": true, "self": 174.2150602320071 }, "steps_from_proto": { "total": 32.924455437984534, "count": 18201, "is_parallel": true, "self": 6.375997721995532, "children": { "_process_rank_one_or_two_observation": { "total": 26.548457715989002, "count": 182010, "is_parallel": true, "self": 26.548457715989002 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001109209999867744, "count": 1, "self": 0.0001109209999867744, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.8281869330225, "count": 652966, "is_parallel": true, "self": 13.30779086903351, "children": { "process_trajectory": { "total": 244.7846818419889, "count": 652966, "is_parallel": true, "self": 244.10775894798894, "children": { "RLTrainer._checkpoint": { "total": 0.6769228939999721, "count": 4, "is_parallel": true, "self": 0.6769228939999721 } } }, "_update_policy": { "total": 184.73571422200007, "count": 90, "is_parallel": true, "self": 56.255456922998405, "children": { "TorchPPOOptimizer.update": { "total": 128.48025729900166, "count": 4587, "is_parallel": true, "self": 128.48025729900166 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08696257100018556, "count": 1, "self": 0.0009020340000915894, "children": { "RLTrainer._checkpoint": { "total": 0.08606053700009397, "count": 1, "self": 0.08606053700009397 } } } } } } }