{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7878207564353943, "min": 0.7817181944847107, "max": 2.863300323486328, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7487.4482421875, "min": 7487.4482421875, "max": 29228.5703125, "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": 12.79130744934082, "min": 0.17860229313373566, "max": 12.79130744934082, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2494.304931640625, "min": 34.64884567260742, "max": 2584.1181640625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06975128316568491, "min": 0.05977035976887004, "max": 0.07733402457272984, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27900513266273963, "min": 0.2527874469330224, "max": 0.37314464687369764, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23066402927917593, "min": 0.13824647811684282, "max": 0.3023194228755493, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9226561171167037, "min": 0.5529859124673713, "max": 1.4467915162151936, "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": 25.272727272727273, "min": 3.272727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1112.0, "min": 144.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.272727272727273, "min": 3.272727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1112.0, "min": 144.0, "max": 1387.0, "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": "1731078578", "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=SnowballTarget1 --no-graphics --force", "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": "1731079011" }, "total": 432.96784509099996, "count": 1, "self": 0.4241922350000209, "children": { "run_training.setup": { "total": 0.06486429399996041, "count": 1, "self": 0.06486429399996041 }, "TrainerController.start_learning": { "total": 432.478788562, "count": 1, "self": 0.3805963070089433, "children": { "TrainerController._reset_env": { "total": 1.9520485250000092, "count": 1, "self": 1.9520485250000092 }, "TrainerController.advance": { "total": 430.0622847909911, "count": 18192, "self": 0.38829122900000357, "children": { "env_step": { "total": 304.0887151029966, "count": 18192, "self": 231.80812633000397, "children": { "SubprocessEnvManager._take_step": { "total": 72.05398572699073, "count": 18192, "self": 1.2625964079769005, "children": { "TorchPolicy.evaluate": { "total": 70.79138931901383, "count": 18192, "self": 70.79138931901383 } } }, "workers": { "total": 0.2266030460019124, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 430.916336033997, "count": 18192, "is_parallel": true, "self": 228.2232574899939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022082350000118822, "count": 1, "is_parallel": true, "self": 0.0006486760001394032, "children": { "_process_rank_one_or_two_observation": { "total": 0.001559558999872479, "count": 10, "is_parallel": true, "self": 0.001559558999872479 } } }, "UnityEnvironment.step": { "total": 0.03627416199998379, "count": 1, "is_parallel": true, "self": 0.0006466829999567381, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040559400002848633, "count": 1, "is_parallel": true, "self": 0.00040559400002848633 }, "communicator.exchange": { "total": 0.033368547999998555, "count": 1, "is_parallel": true, "self": 0.033368547999998555 }, "steps_from_proto": { "total": 0.0018533370000000104, "count": 1, "is_parallel": true, "self": 0.00034103399997320594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015123030000268045, "count": 10, "is_parallel": true, "self": 0.0015123030000268045 } } } } } } }, "UnityEnvironment.step": { "total": 202.69307854400313, "count": 18191, "is_parallel": true, "self": 10.091306276989656, "children": { "UnityEnvironment._generate_step_input": { "total": 5.428622065002912, "count": 18191, "is_parallel": true, "self": 5.428622065002912 }, "communicator.exchange": { "total": 154.7535699120058, "count": 18191, "is_parallel": true, "self": 154.7535699120058 }, "steps_from_proto": { "total": 32.419580290004774, "count": 18191, "is_parallel": true, "self": 5.989876836009557, "children": { "_process_rank_one_or_two_observation": { "total": 26.429703453995216, "count": 181910, "is_parallel": true, "self": 26.429703453995216 } } } } } } } } } } }, "trainer_advance": { "total": 125.58527845899448, "count": 18192, "self": 0.4599554709966469, "children": { "process_trajectory": { "total": 28.007386342997393, "count": 18192, "self": 27.560398616997304, "children": { "RLTrainer._checkpoint": { "total": 0.4469877260000885, "count": 4, "self": 0.4469877260000885 } } }, "_update_policy": { "total": 97.11793664500044, "count": 90, "self": 40.04097367300784, "children": { "TorchPPOOptimizer.update": { "total": 57.0769629719926, "count": 4587, "self": 57.0769629719926 } } } } } } }, "trainer_threads": { "total": 9.259999842470279e-07, "count": 1, "self": 9.259999842470279e-07 }, "TrainerController._save_models": { "total": 0.08385801299994, "count": 1, "self": 0.0009024669999462276, "children": { "RLTrainer._checkpoint": { "total": 0.08295554599999377, "count": 1, "self": 0.08295554599999377 } } } } } } }