{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0972331762313843, "min": 1.0960239171981812, "max": 2.870147228240967, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10500.521484375, "min": 10500.521484375, "max": 29424.75, "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": 12.625933647155762, "min": 0.2953099012374878, "max": 12.625933647155762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2462.05712890625, "min": 57.29011917114258, "max": 2533.47509765625, "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": 0.06863949065454482, "min": 0.06328946853787498, "max": 0.07577976958404464, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2745579626181793, "min": 0.25315787415149993, "max": 0.3729711159876566, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24188769594127058, "min": 0.09430107182147456, "max": 0.2731768800055279, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9675507837650823, "min": 0.3772042872858982, "max": 1.3384781658065086, "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": 24.65909090909091, "min": 2.75, "max": 24.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1085.0, "min": 121.0, "max": 1367.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.65909090909091, "min": 2.75, "max": 24.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1085.0, "min": 121.0, "max": 1367.0, "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": "1679927879", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1679928337" }, "total": 458.0566088280001, "count": 1, "self": 0.4325728459999709, "children": { "run_training.setup": { "total": 0.12492306100000405, "count": 1, "self": 0.12492306100000405 }, "TrainerController.start_learning": { "total": 457.4991129210001, "count": 1, "self": 0.5143260680023332, "children": { "TrainerController._reset_env": { "total": 9.733311639000021, "count": 1, "self": 9.733311639000021 }, "TrainerController.advance": { "total": 447.11338399799774, "count": 18204, "self": 0.2561119199838231, "children": { "env_step": { "total": 446.8572720780139, "count": 18204, "self": 324.4566089810287, "children": { "SubprocessEnvManager._take_step": { "total": 122.14358778298936, "count": 18204, "self": 1.819869161978545, "children": { "TorchPolicy.evaluate": { "total": 120.32371862101081, "count": 18204, "self": 120.32371862101081 } } }, "workers": { "total": 0.2570753139958697, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 456.08753402397997, "count": 18204, "is_parallel": true, "self": 219.00516036996203, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00589995200004978, "count": 1, "is_parallel": true, "self": 0.004225444999860883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016745070001888962, "count": 10, "is_parallel": true, "self": 0.0016745070001888962 } } }, "UnityEnvironment.step": { "total": 0.04321565699990515, "count": 1, "is_parallel": true, "self": 0.000773148999883233, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038805899998806126, "count": 1, "is_parallel": true, "self": 0.00038805899998806126 }, "communicator.exchange": { "total": 0.04019823800001632, "count": 1, "is_parallel": true, "self": 0.04019823800001632 }, "steps_from_proto": { "total": 0.001856211000017538, "count": 1, "is_parallel": true, "self": 0.0004056870000113122, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014505240000062258, "count": 10, "is_parallel": true, "self": 0.0014505240000062258 } } } } } } }, "UnityEnvironment.step": { "total": 237.08237365401794, "count": 18203, "is_parallel": true, "self": 9.371061795994137, "children": { "UnityEnvironment._generate_step_input": { "total": 5.194433585012689, "count": 18203, "is_parallel": true, "self": 5.194433585012689 }, "communicator.exchange": { "total": 192.06282949100444, "count": 18203, "is_parallel": true, "self": 192.06282949100444 }, "steps_from_proto": { "total": 30.45404878200668, "count": 18203, "is_parallel": true, "self": 5.947185700003729, "children": { "_process_rank_one_or_two_observation": { "total": 24.50686308200295, "count": 182030, "is_parallel": true, "self": 24.50686308200295 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013488900003721938, "count": 1, "self": 0.00013488900003721938, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.8231311921444, "count": 398180, "is_parallel": true, "self": 9.52986437008201, "children": { "process_trajectory": { "total": 246.72447359006242, "count": 398180, "is_parallel": true, "self": 245.64712395906258, "children": { "RLTrainer._checkpoint": { "total": 1.0773496309998336, "count": 4, "is_parallel": true, "self": 1.0773496309998336 } } }, "_update_policy": { "total": 187.56879323199996, "count": 90, "is_parallel": true, "self": 70.57140111499552, "children": { "TorchPPOOptimizer.update": { "total": 116.99739211700444, "count": 4587, "is_parallel": true, "self": 116.99739211700444 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1379563269999835, "count": 1, "self": 0.0008512829999745009, "children": { "RLTrainer._checkpoint": { "total": 0.137105044000009, "count": 1, "self": 0.137105044000009 } } } } } } }