{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9113184213638306, "min": 0.9090355634689331, "max": 2.8717827796936035, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8701.2685546875, "min": 8701.2685546875, "max": 29409.927734375, "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": 13.011133193969727, "min": 0.3590526878833771, "max": 13.011133193969727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2537.1708984375, "min": 69.65621948242188, "max": 2617.486328125, "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": 0.0646619699905654, "min": 0.06291096510481023, "max": 0.07683152416589734, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2586478799622616, "min": 0.2530403850259437, "max": 0.3514705897647289, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20500964360932508, "min": 0.11586229769198006, "max": 0.3278738374803581, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8200385744373003, "min": 0.46344919076792024, "max": 1.6393691874017904, "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": 25.977272727272727, "min": 3.3181818181818183, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 146.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.3181818181818183, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 146.0, "max": 1404.0, "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": "1700124029", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700124491" }, "total": 462.0378491759999, "count": 1, "self": 0.7501384749998579, "children": { "run_training.setup": { "total": 0.045217633999982354, "count": 1, "self": 0.045217633999982354 }, "TrainerController.start_learning": { "total": 461.24249306700005, "count": 1, "self": 0.5185720800063791, "children": { "TrainerController._reset_env": { "total": 8.66457380899999, "count": 1, "self": 8.66457380899999 }, "TrainerController.advance": { "total": 451.9382213409938, "count": 18212, "self": 0.2489067399983469, "children": { "env_step": { "total": 451.68931460099543, "count": 18212, "self": 310.9287938429966, "children": { "SubprocessEnvManager._take_step": { "total": 140.4971291769981, "count": 18212, "self": 1.3917462710104473, "children": { "TorchPolicy.evaluate": { "total": 139.10538290598765, "count": 18212, "self": 139.10538290598765 } } }, "workers": { "total": 0.26339158100074656, "count": 18212, "self": 0.0, "children": { "worker_root": { "total": 459.9146714149899, "count": 18212, "is_parallel": true, "self": 226.43436241700545, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005226352000022416, "count": 1, "is_parallel": true, "self": 0.003809357999898566, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014169940001238501, "count": 10, "is_parallel": true, "self": 0.0014169940001238501 } } }, "UnityEnvironment.step": { "total": 0.04266572900007759, "count": 1, "is_parallel": true, "self": 0.0004238990001113052, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031736799996906484, "count": 1, "is_parallel": true, "self": 0.00031736799996906484 }, "communicator.exchange": { "total": 0.04068675799999255, "count": 1, "is_parallel": true, "self": 0.04068675799999255 }, "steps_from_proto": { "total": 0.001237704000004669, "count": 1, "is_parallel": true, "self": 0.00028160099998331134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009561030000213577, "count": 10, "is_parallel": true, "self": 0.0009561030000213577 } } } } } } }, "UnityEnvironment.step": { "total": 233.48030899798448, "count": 18211, "is_parallel": true, "self": 10.337997987967583, "children": { "UnityEnvironment._generate_step_input": { "total": 5.199351187992306, "count": 18211, "is_parallel": true, "self": 5.199351187992306 }, "communicator.exchange": { "total": 185.3180657220173, "count": 18211, "is_parallel": true, "self": 185.3180657220173 }, "steps_from_proto": { "total": 32.62489410000728, "count": 18211, "is_parallel": true, "self": 5.948028594000675, "children": { "_process_rank_one_or_two_observation": { "total": 26.676865506006607, "count": 182110, "is_parallel": true, "self": 26.676865506006607 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022711199994773779, "count": 1, "self": 0.00022711199994773779, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.08198619196094, "count": 486492, "is_parallel": true, "self": 10.098877527932018, "children": { "process_trajectory": { "total": 252.77547964402913, "count": 486492, "is_parallel": true, "self": 251.72377183902904, "children": { "RLTrainer._checkpoint": { "total": 1.0517078050000919, "count": 4, "is_parallel": true, "self": 1.0517078050000919 } } }, "_update_policy": { "total": 185.20762901999979, "count": 90, "is_parallel": true, "self": 61.26547755499735, "children": { "TorchPPOOptimizer.update": { "total": 123.94215146500244, "count": 4584, "is_parallel": true, "self": 123.94215146500244 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1208987249999609, "count": 1, "self": 0.001087687999870468, "children": { "RLTrainer._checkpoint": { "total": 0.11981103700009044, "count": 1, "self": 0.11981103700009044 } } } } } } }