{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8943982124328613, "min": 0.8909622430801392, "max": 2.8681466579437256, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8638.09765625, "min": 8638.09765625, "max": 29341.140625, "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": 13.053723335266113, "min": 0.422027587890625, "max": 13.053723335266113, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2545.47607421875, "min": 81.87335205078125, "max": 2643.33203125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07323263370398862, "min": 0.062336208808404736, "max": 0.07323263370398862, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2929305348159545, "min": 0.24934483523361894, "max": 0.36185408579602185, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1972630731441884, "min": 0.12046865805727885, "max": 0.2987561689872368, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7890522925767536, "min": 0.4818746322291154, "max": 1.4937808449361838, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.130097290000004e-06, "min": 8.130097290000004e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2520389160000015e-05, "min": 3.2520389160000015e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10271, "min": 0.10271, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41084, "min": 0.41084, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014522900000000006, "min": 0.00014522900000000006, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005809160000000002, "min": 0.0005809160000000002, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.40909090909091, "min": 3.2954545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 145.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 3.2954545454545454, "max": 25.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 145.0, "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": "1704915049", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704915495" }, "total": 446.193680865, "count": 1, "self": 0.6332390759999953, "children": { "run_training.setup": { "total": 0.05243972299996358, "count": 1, "self": 0.05243972299996358 }, "TrainerController.start_learning": { "total": 445.508002066, "count": 1, "self": 0.5713476310068586, "children": { "TrainerController._reset_env": { "total": 3.771073367999975, "count": 1, "self": 3.771073367999975 }, "TrainerController.advance": { "total": 441.02746144099325, "count": 18222, "self": 0.2725543289899406, "children": { "env_step": { "total": 440.7549071120033, "count": 18222, "self": 289.3145701179967, "children": { "SubprocessEnvManager._take_step": { "total": 151.1565702410137, "count": 18222, "self": 1.4592497520160919, "children": { "TorchPolicy.evaluate": { "total": 149.6973204889976, "count": 18222, "self": 149.6973204889976 } } }, "workers": { "total": 0.28376675299290355, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 444.2141573819988, "count": 18222, "is_parallel": true, "self": 220.2036694660058, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005006431000026623, "count": 1, "is_parallel": true, "self": 0.0036602750000156448, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013461560000109785, "count": 10, "is_parallel": true, "self": 0.0013461560000109785 } } }, "UnityEnvironment.step": { "total": 0.038547496999967734, "count": 1, "is_parallel": true, "self": 0.0007325659999537493, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004107149999867943, "count": 1, "is_parallel": true, "self": 0.0004107149999867943 }, "communicator.exchange": { "total": 0.03539649399999689, "count": 1, "is_parallel": true, "self": 0.03539649399999689 }, "steps_from_proto": { "total": 0.0020077220000302987, "count": 1, "is_parallel": true, "self": 0.00040440200007196836, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016033199999583303, "count": 10, "is_parallel": true, "self": 0.0016033199999583303 } } } } } } }, "UnityEnvironment.step": { "total": 224.010487915993, "count": 18221, "is_parallel": true, "self": 10.74182955200962, "children": { "UnityEnvironment._generate_step_input": { "total": 5.303732006989662, "count": 18221, "is_parallel": true, "self": 5.303732006989662 }, "communicator.exchange": { "total": 174.5180152489965, "count": 18221, "is_parallel": true, "self": 174.5180152489965 }, "steps_from_proto": { "total": 33.44691110799721, "count": 18221, "is_parallel": true, "self": 6.117302822006934, "children": { "_process_rank_one_or_two_observation": { "total": 27.329608285990275, "count": 182210, "is_parallel": true, "self": 27.329608285990275 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013669199995547388, "count": 1, "self": 0.00013669199995547388, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 435.64405899799607, "count": 672662, "is_parallel": true, "self": 14.528416616025652, "children": { "process_trajectory": { "total": 240.30686943797002, "count": 672662, "is_parallel": true, "self": 239.3624485569701, "children": { "RLTrainer._checkpoint": { "total": 0.9444208809999282, "count": 4, "is_parallel": true, "self": 0.9444208809999282 } } }, "_update_policy": { "total": 180.8087729440004, "count": 90, "is_parallel": true, "self": 57.78577712900011, "children": { "TorchPPOOptimizer.update": { "total": 123.02299581500029, "count": 4584, "is_parallel": true, "self": 123.02299581500029 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13798293399997874, "count": 1, "self": 0.0013340849999394777, "children": { "RLTrainer._checkpoint": { "total": 0.13664884900003926, "count": 1, "self": 0.13664884900003926 } } } } } } }