{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0367941856384277, "min": 1.0367941856384277, "max": 1.0655056238174438, "count": 5 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10435.333984375, "min": 10311.0283203125, "max": 10915.4716796875, "count": 5 }, "SnowballTarget.Step.mean": { "value": 349976.0, "min": 309992.0, "max": 349976.0, "count": 5 }, "SnowballTarget.Step.sum": { "value": 349976.0, "min": 309992.0, "max": 349976.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.040831565856934, "min": 13.79809856414795, "max": 14.040831565856934, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 4844.0869140625, "min": 4691.353515625, "max": 4931.90771484375, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0658794366727485, "min": 0.06211032461826963, "max": 0.0706150818019238, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.263517746690994, "min": 0.263517746690994, "max": 0.3472825798740172, "count": 5 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15005831745471437, "min": 0.15005831745471437, "max": 0.17657990674762164, "count": 5 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6002332698188575, "min": 0.6002332698188575, "max": 0.8828995337381083, "count": 5 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.885812908571415e-06, "min": 6.885812908571415e-06, "max": 6.345723016571427e-05, "count": 5 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.754325163428566e-05, "min": 2.754325163428566e-05, "max": 0.0002538289206628571, "count": 5 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10137714285714286, "min": 0.10137714285714286, "max": 0.11269142857142858, "count": 5 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40550857142857144, "min": 0.40550857142857144, "max": 0.5493142857142858, "count": 5 }, "SnowballTarget.Policy.Beta.mean": { "value": 7.871942857142844e-05, "min": 7.871942857142844e-05, "max": 0.0006433022857142858, "count": 5 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003148777142857138, "min": 0.0003148777142857138, "max": 0.002573209142857143, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.15909090909091, "min": 26.59090909090909, "max": 28.15909090909091, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1239.0, "min": 1170.0, "max": 1514.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.15909090909091, "min": 26.59090909090909, "max": 28.15909090909091, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1239.0, "min": 1170.0, "max": 1514.0, "count": 5 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1731683702", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=SnowballTarget3 --resume --torch-device cuda:0 --no-graphics --debug", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731683829" }, "total": 127.34562296200056, "count": 1, "self": 0.42530555900066247, "children": { "run_training.setup": { "total": 0.05668498900013219, "count": 1, "self": 0.05668498900013219 }, "TrainerController.start_learning": { "total": 126.86363241399977, "count": 1, "self": 0.2151459170263479, "children": { "TrainerController._reset_env": { "total": 2.091820235999876, "count": 1, "self": 2.091820235999876 }, "TrainerController.advance": { "total": 124.43796483097412, "count": 4565, "self": 0.06627403594575298, "children": { "env_step": { "total": 124.37169079502837, "count": 4565, "self": 77.4977750210328, "children": { "SubprocessEnvManager._take_step": { "total": 46.80662975798077, "count": 4565, "self": 0.3603283040047245, "children": { "TorchPolicy.evaluate": { "total": 46.44630145397605, "count": 4565, "self": 46.44630145397605 } } }, "workers": { "total": 0.06728601601480477, "count": 4565, "self": 0.0, "children": { "worker_root": { "total": 126.45530187803524, "count": 4565, "is_parallel": true, "self": 74.12169770105811, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023176779995992547, "count": 1, "is_parallel": true, "self": 0.0007073850010783644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016102929985208903, "count": 10, "is_parallel": true, "self": 0.0016102929985208903 } } }, "UnityEnvironment.step": { "total": 0.03498332399976789, "count": 1, "is_parallel": true, "self": 0.0006267919998208527, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005173250001462293, "count": 1, "is_parallel": true, "self": 0.0005173250001462293 }, "communicator.exchange": { "total": 0.03198084399991785, "count": 1, "is_parallel": true, "self": 0.03198084399991785 }, "steps_from_proto": { "total": 0.0018583629998829565, "count": 1, "is_parallel": true, "self": 0.0003658820023701992, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014924809975127573, "count": 10, "is_parallel": true, "self": 0.0014924809975127573 } } } } } } }, "UnityEnvironment.step": { "total": 52.33360417697713, "count": 4564, "is_parallel": true, "self": 2.4787895938789006, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3280006540717295, "count": 4564, "is_parallel": true, "self": 1.3280006540717295 }, "communicator.exchange": { "total": 40.516957113009994, "count": 4564, "is_parallel": true, "self": 40.516957113009994 }, "steps_from_proto": { "total": 8.009856816016509, "count": 4564, "is_parallel": true, "self": 1.501679792010691, "children": { "_process_rank_one_or_two_observation": { "total": 6.508177024005818, "count": 45640, "is_parallel": true, "self": 6.508177024005818 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012469299963413505, "count": 1, "self": 0.00012469299963413505, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 123.16921977485345, "count": 160201, "is_parallel": true, "self": 3.418663629007824, "children": { "process_trajectory": { "total": 86.42869974484529, "count": 160201, "is_parallel": true, "self": 86.20989998884488, "children": { "RLTrainer._checkpoint": { "total": 0.2187997560004078, "count": 1, "is_parallel": true, "self": 0.2187997560004078 } } }, "_update_policy": { "total": 33.32185640100033, "count": 22, "is_parallel": true, "self": 11.566497000006166, "children": { "TorchPPOOptimizer.update": { "total": 21.755359400994166, "count": 1119, "is_parallel": true, "self": 21.755359400994166 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11857673699978477, "count": 1, "self": 0.0011199229993508197, "children": { "RLTrainer._checkpoint": { "total": 0.11745681400043395, "count": 1, "self": 0.11745681400043395 } } } } } } }