{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0754239559173584, "min": 1.0754239559173584, "max": 2.8491103649139404, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10315.466796875, "min": 10315.466796875, "max": 29177.73828125, "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": 12.468709945678711, "min": 0.3454476594924927, "max": 12.468709945678711, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2431.3984375, "min": 67.016845703125, "max": 2526.640625, "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": 0.06978167955329648, "min": 0.0634384319576152, "max": 0.07572595935219878, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2791267182131859, "min": 0.26032307795842413, "max": 0.3546620882945146, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.216440100222826, "min": 0.11593264300609007, "max": 0.29806401297157886, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.865760400891304, "min": 0.4637305720243603, "max": 1.4903200648578943, "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": 24.545454545454547, "min": 3.3181818181818183, "max": 24.563636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1080.0, "min": 146.0, "max": 1351.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.545454545454547, "min": 3.3181818181818183, "max": 24.563636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1080.0, "min": 146.0, "max": 1351.0, "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": "1701173470", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701173973" }, "total": 503.20595121299993, "count": 1, "self": 0.6281732980000925, "children": { "run_training.setup": { "total": 0.056630026999982874, "count": 1, "self": 0.056630026999982874 }, "TrainerController.start_learning": { "total": 502.52114788799986, "count": 1, "self": 0.597386738007117, "children": { "TrainerController._reset_env": { "total": 3.2978635959999565, "count": 1, "self": 3.2978635959999565 }, "TrainerController.advance": { "total": 498.4949427519929, "count": 18208, "self": 0.3166687919930382, "children": { "env_step": { "total": 498.17827395999984, "count": 18208, "self": 338.1480770190067, "children": { "SubprocessEnvManager._take_step": { "total": 159.72029375400155, "count": 18208, "self": 1.5391782729985835, "children": { "TorchPolicy.evaluate": { "total": 158.18111548100296, "count": 18208, "self": 158.18111548100296 } } }, "workers": { "total": 0.3099031869916189, "count": 18208, "self": 0.0, "children": { "worker_root": { "total": 501.06138416400756, "count": 18208, "is_parallel": true, "self": 245.36106247500572, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004889170999945236, "count": 1, "is_parallel": true, "self": 0.0033845309998241646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015046400001210714, "count": 10, "is_parallel": true, "self": 0.0015046400001210714 } } }, "UnityEnvironment.step": { "total": 0.059212819999970634, "count": 1, "is_parallel": true, "self": 0.0006581659998801115, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040952900008051074, "count": 1, "is_parallel": true, "self": 0.00040952900008051074 }, "communicator.exchange": { "total": 0.0560276740000063, "count": 1, "is_parallel": true, "self": 0.0560276740000063 }, "steps_from_proto": { "total": 0.0021174510000037117, "count": 1, "is_parallel": true, "self": 0.0003833170000007158, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017341340000029959, "count": 10, "is_parallel": true, "self": 0.0017341340000029959 } } } } } } }, "UnityEnvironment.step": { "total": 255.70032168900184, "count": 18207, "is_parallel": true, "self": 11.233851602008599, "children": { "UnityEnvironment._generate_step_input": { "total": 5.744747306997851, "count": 18207, "is_parallel": true, "self": 5.744747306997851 }, "communicator.exchange": { "total": 201.547408055005, "count": 18207, "is_parallel": true, "self": 201.547408055005 }, "steps_from_proto": { "total": 37.17431472499038, "count": 18207, "is_parallel": true, "self": 7.089745190026747, "children": { "_process_rank_one_or_two_observation": { "total": 30.084569534963634, "count": 182070, "is_parallel": true, "self": 30.084569534963634 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00019443299993326946, "count": 1, "self": 0.00019443299993326946, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 494.043177466006, "count": 534170, "is_parallel": true, "self": 11.943981519016802, "children": { "process_trajectory": { "total": 280.7688851769891, "count": 534170, "is_parallel": true, "self": 279.87450297098917, "children": { "RLTrainer._checkpoint": { "total": 0.894382205999932, "count": 4, "is_parallel": true, "self": 0.894382205999932 } } }, "_update_policy": { "total": 201.3303107700001, "count": 90, "is_parallel": true, "self": 63.39183269499654, "children": { "TorchPPOOptimizer.update": { "total": 137.93847807500356, "count": 4587, "is_parallel": true, "self": 137.93847807500356 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13076036899997234, "count": 1, "self": 0.0011830010000721813, "children": { "RLTrainer._checkpoint": { "total": 0.12957736799990016, "count": 1, "self": 0.12957736799990016 } } } } } } }