{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9986892938613892, "min": 0.9986892938613892, "max": 2.8758599758148193, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9535.4853515625, "min": 9535.4853515625, "max": 29451.681640625, "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": 12.536701202392578, "min": 0.31614547967910767, "max": 12.536701202392578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2444.65673828125, "min": 61.33222198486328, "max": 2520.564697265625, "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.Losses.PolicyLoss.mean": { "value": 0.07051382079489664, "min": 0.060650754914996816, "max": 0.0755278407824317, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28205528317958656, "min": 0.24260301965998726, "max": 0.35753934306101687, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18891281565176507, "min": 0.11715736132293172, "max": 0.299556233281014, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7556512626070603, "min": 0.4686294452917269, "max": 1.3371317462593904, "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": 24.636363636363637, "min": 3.25, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 143.0, "max": 1365.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.25, "max": 24.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 143.0, "max": 1365.0, "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": "1692536198", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1692536695" }, "total": 496.827043365, "count": 1, "self": 0.4328564330000404, "children": { "run_training.setup": { "total": 0.04226877399997875, "count": 1, "self": 0.04226877399997875 }, "TrainerController.start_learning": { "total": 496.351918158, "count": 1, "self": 0.5627913040072485, "children": { "TrainerController._reset_env": { "total": 5.250992889000031, "count": 1, "self": 5.250992889000031 }, "TrainerController.advance": { "total": 490.39174324199274, "count": 18201, "self": 0.27864037999131597, "children": { "env_step": { "total": 490.1131028620014, "count": 18201, "self": 354.6491145290028, "children": { "SubprocessEnvManager._take_step": { "total": 135.17102357900063, "count": 18201, "self": 1.8244640789975506, "children": { "TorchPolicy.evaluate": { "total": 133.34655950000308, "count": 18201, "self": 133.34655950000308 } } }, "workers": { "total": 0.2929647539979783, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 494.64639429000255, "count": 18201, "is_parallel": true, "self": 233.9524561840068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005465828000012607, "count": 1, "is_parallel": true, "self": 0.0037911250000206564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016747029999919505, "count": 10, "is_parallel": true, "self": 0.0016747029999919505 } } }, "UnityEnvironment.step": { "total": 0.10585548900002095, "count": 1, "is_parallel": true, "self": 0.0006834170000047379, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045146400003659437, "count": 1, "is_parallel": true, "self": 0.00045146400003659437 }, "communicator.exchange": { "total": 0.10014725299998872, "count": 1, "is_parallel": true, "self": 0.10014725299998872 }, "steps_from_proto": { "total": 0.004573354999990897, "count": 1, "is_parallel": true, "self": 0.00044090999995205493, "children": { "_process_rank_one_or_two_observation": { "total": 0.004132445000038842, "count": 10, "is_parallel": true, "self": 0.004132445000038842 } } } } } } }, "UnityEnvironment.step": { "total": 260.69393810599576, "count": 18200, "is_parallel": true, "self": 11.079587198983972, "children": { "UnityEnvironment._generate_step_input": { "total": 5.73835589700019, "count": 18200, "is_parallel": true, "self": 5.73835589700019 }, "communicator.exchange": { "total": 204.54043135499796, "count": 18200, "is_parallel": true, "self": 204.54043135499796 }, "steps_from_proto": { "total": 39.33556365501363, "count": 18200, "is_parallel": true, "self": 7.090789572025869, "children": { "_process_rank_one_or_two_observation": { "total": 32.24477408298776, "count": 182000, "is_parallel": true, "self": 32.24477408298776 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012928399996781081, "count": 1, "self": 0.00012928399996781081, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 486.2545038689832, "count": 475121, "is_parallel": true, "self": 11.410883775006653, "children": { "process_trajectory": { "total": 268.4815872839767, "count": 475121, "is_parallel": true, "self": 267.08097801497655, "children": { "RLTrainer._checkpoint": { "total": 1.4006092690001424, "count": 4, "is_parallel": true, "self": 1.4006092690001424 } } }, "_update_policy": { "total": 206.36203280999985, "count": 90, "is_parallel": true, "self": 80.25403578100304, "children": { "TorchPPOOptimizer.update": { "total": 126.1079970289968, "count": 4587, "is_parallel": true, "self": 126.1079970289968 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14626143899999988, "count": 1, "self": 0.0008570880000888792, "children": { "RLTrainer._checkpoint": { "total": 0.145404350999911, "count": 1, "self": 0.145404350999911 } } } } } } }