{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0261528491973877, "min": 1.0099730491638184, "max": 2.862191677093506, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9854.1455078125, "min": 9854.1455078125, "max": 29437.640625, "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": 12.751107215881348, "min": 0.4476368725299835, "max": 12.751107215881348, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2486.4658203125, "min": 86.841552734375, "max": 2538.83740234375, "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": 0.07011297053523936, "min": 0.06167585188599974, "max": 0.07595182980488364, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28045188214095745, "min": 0.24670340754399897, "max": 0.3739430310456288, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21565922503085697, "min": 0.1297128173207645, "max": 0.2744180365520365, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8626369001234279, "min": 0.518851269283058, "max": 1.3720901827601826, "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": 25.613636363636363, "min": 3.7954545454545454, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 167.0, "max": 1369.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.7954545454545454, "max": 25.613636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 167.0, "max": 1369.0, "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": "1716469203", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/media/fast/code/learning/venv_learning/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716469470" }, "total": 266.7609347400721, "count": 1, "self": 0.2684390670619905, "children": { "run_training.setup": { "total": 0.14263686502818018, "count": 1, "self": 0.14263686502818018 }, "TrainerController.start_learning": { "total": 266.34985880798195, "count": 1, "self": 0.3428611521376297, "children": { "TrainerController._reset_env": { "total": 1.2291536779375747, "count": 1, "self": 1.2291536779375747 }, "TrainerController.advance": { "total": 264.7284476229688, "count": 18207, "self": 0.1643518463242799, "children": { "env_step": { "total": 264.56409577664454, "count": 18207, "self": 146.3410327314632, "children": { "SubprocessEnvManager._take_step": { "total": 118.03569965087809, "count": 18207, "self": 0.8054905446479097, "children": { "TorchPolicy.evaluate": { "total": 117.23020910623018, "count": 18207, "self": 117.23020910623018 } } }, "workers": { "total": 0.18736339430324733, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 266.03338430728763, "count": 18207, "is_parallel": true, "self": 170.69119834911544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015260200016200542, "count": 1, "is_parallel": true, "self": 0.0007046321406960487, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008213878609240055, "count": 10, "is_parallel": true, "self": 0.0008213878609240055 } } }, "UnityEnvironment.step": { "total": 0.014016034081578255, "count": 1, "is_parallel": true, "self": 0.00019926519598811865, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014918192755430937, "count": 1, "is_parallel": true, "self": 0.00014918192755430937 }, "communicator.exchange": { "total": 0.013066648971289396, "count": 1, "is_parallel": true, "self": 0.013066648971289396 }, "steps_from_proto": { "total": 0.0006009379867464304, "count": 1, "is_parallel": true, "self": 0.00013992679305374622, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004610111936926842, "count": 10, "is_parallel": true, "self": 0.0004610111936926842 } } } } } } }, "UnityEnvironment.step": { "total": 95.3421859581722, "count": 18206, "is_parallel": true, "self": 3.6139822638360783, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2517413379391655, "count": 18206, "is_parallel": true, "self": 2.2517413379391655 }, "communicator.exchange": { "total": 78.41511161974631, "count": 18206, "is_parallel": true, "self": 78.41511161974631 }, "steps_from_proto": { "total": 11.061350736650638, "count": 18206, "is_parallel": true, "self": 2.4962622311431915, "children": { "_process_rank_one_or_two_observation": { "total": 8.565088505507447, "count": 182060, "is_parallel": true, "self": 8.565088505507447 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.19389645382762e-05, "count": 1, "self": 7.19389645382762e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 264.25358994305134, "count": 292827, "is_parallel": true, "self": 1.9259759547421709, "children": { "process_trajectory": { "total": 150.56986518437043, "count": 292827, "is_parallel": true, "self": 150.20912238454912, "children": { "RLTrainer._checkpoint": { "total": 0.36074279982130975, "count": 4, "is_parallel": true, "self": 0.36074279982130975 } } }, "_update_policy": { "total": 111.75774880393874, "count": 90, "is_parallel": true, "self": 20.899067089078017, "children": { "TorchPPOOptimizer.update": { "total": 90.85868171486072, "count": 4587, "is_parallel": true, "self": 90.85868171486072 } } } } } } } } }, "TrainerController._save_models": { "total": 0.04932441597338766, "count": 1, "self": 0.00046101200859993696, "children": { "RLTrainer._checkpoint": { "total": 0.04886340396478772, "count": 1, "self": 0.04886340396478772 } } } } } } }