{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8977257609367371, "min": 0.8977257609367371, "max": 2.86251163482666, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8531.9853515625, "min": 8531.9853515625, "max": 29220.51953125, "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": 13.107364654541016, "min": 0.5002454519271851, "max": 13.107364654541016, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2555.93603515625, "min": 97.04761505126953, "max": 2649.0908203125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0639887152049364, "min": 0.0639887152049364, "max": 0.07282605379712587, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2559548608197456, "min": 0.2559548608197456, "max": 0.3616931393084015, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17713007951776186, "min": 0.12355667986340968, "max": 0.3045653267818339, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7085203180710474, "min": 0.4942267194536387, "max": 1.5228266339091694, "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": 25.886363636363637, "min": 3.4318181818181817, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 151.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.4318181818181817, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 151.0, "max": 1401.0, "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": "1752155389", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752155819" }, "total": 429.4330978219999, "count": 1, "self": 0.43380074699996385, "children": { "run_training.setup": { "total": 0.031333387000017865, "count": 1, "self": 0.031333387000017865 }, "TrainerController.start_learning": { "total": 428.96796368799994, "count": 1, "self": 0.3525055680031528, "children": { "TrainerController._reset_env": { "total": 3.360959037999919, "count": 1, "self": 3.360959037999919 }, "TrainerController.advance": { "total": 425.1743385909966, "count": 18192, "self": 0.37608477100013715, "children": { "env_step": { "total": 306.10554397100873, "count": 18192, "self": 234.96431885000402, "children": { "SubprocessEnvManager._take_step": { "total": 70.92574886500313, "count": 18192, "self": 1.2771598560005941, "children": { "TorchPolicy.evaluate": { "total": 69.64858900900254, "count": 18192, "self": 69.64858900900254 } } }, "workers": { "total": 0.2154762560015797, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 427.59797163700557, "count": 18192, "is_parallel": true, "self": 221.11749092900823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005615990000023885, "count": 1, "is_parallel": true, "self": 0.0035661200000731696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020498699999507153, "count": 10, "is_parallel": true, "self": 0.0020498699999507153 } } }, "UnityEnvironment.step": { "total": 0.03521496400003343, "count": 1, "is_parallel": true, "self": 0.000542626000196833, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000398454999981368, "count": 1, "is_parallel": true, "self": 0.000398454999981368 }, "communicator.exchange": { "total": 0.032423328999925616, "count": 1, "is_parallel": true, "self": 0.032423328999925616 }, "steps_from_proto": { "total": 0.0018505539999296161, "count": 1, "is_parallel": true, "self": 0.00033850499994514394, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015120489999844722, "count": 10, "is_parallel": true, "self": 0.0015120489999844722 } } } } } } }, "UnityEnvironment.step": { "total": 206.48048070799734, "count": 18191, "is_parallel": true, "self": 9.871571103993801, "children": { "UnityEnvironment._generate_step_input": { "total": 5.527114413013123, "count": 18191, "is_parallel": true, "self": 5.527114413013123 }, "communicator.exchange": { "total": 158.51009426600217, "count": 18191, "is_parallel": true, "self": 158.51009426600217 }, "steps_from_proto": { "total": 32.57170092498825, "count": 18191, "is_parallel": true, "self": 5.796537026998067, "children": { "_process_rank_one_or_two_observation": { "total": 26.775163897990183, "count": 181910, "is_parallel": true, "self": 26.775163897990183 } } } } } } } } } } }, "trainer_advance": { "total": 118.69270984898776, "count": 18192, "self": 0.41364469697430195, "children": { "process_trajectory": { "total": 26.286407717012708, "count": 18192, "self": 25.873722836012917, "children": { "RLTrainer._checkpoint": { "total": 0.41268488099979095, "count": 4, "self": 0.41268488099979095 } } }, "_update_policy": { "total": 91.99265743500075, "count": 90, "self": 37.888253019006925, "children": { "TorchPPOOptimizer.update": { "total": 54.10440441599383, "count": 4587, "self": 54.10440441599383 } } } } } } }, "trainer_threads": { "total": 1.044000100591802e-06, "count": 1, "self": 1.044000100591802e-06 }, "TrainerController._save_models": { "total": 0.08015944700014188, "count": 1, "self": 0.000829594000151701, "children": { "RLTrainer._checkpoint": { "total": 0.07932985299999018, "count": 1, "self": 0.07932985299999018 } } } } } } }