{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8778226375579834, "min": 0.8778226375579834, "max": 0.8953980803489685, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9057.3740234375, "min": 9057.3740234375, "max": 9169.771484375, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.390297889709473, "min": 9.703370094299316, "max": 11.390297889709473, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2335.010986328125, "min": 1882.453857421875, "max": 2335.010986328125, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06390206245637006, "min": 0.06390206245637006, "max": 0.06524996074008146, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3195103122818503, "min": 0.26099984296032586, "max": 0.3195103122818503, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1859095601182358, "min": 0.1859095601182358, "max": 0.231412504977711, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.929547800591179, "min": 0.925650019910844, "max": 0.929547800591179, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.072727272727274, "min": 26.072727272727274, "max": 26.09090909090909, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1434.0, "min": 1148.0, "max": 1434.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.072727272727274, "min": 26.072727272727274, "max": 26.09090909090909, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1434.0, "min": 1148.0, "max": 1434.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677333391", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=SnowballTarget --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677333459" }, "total": 68.4048854509997, "count": 1, "self": 0.5297821110002587, "children": { "run_training.setup": { "total": 0.1359855009995954, "count": 1, "self": 0.1359855009995954 }, "TrainerController.start_learning": { "total": 67.73911783899985, "count": 1, "self": 0.1297652010107413, "children": { "TrainerController._reset_env": { "total": 4.1071545260001585, "count": 1, "self": 4.1071545260001585 }, "TrainerController.advance": { "total": 63.34822665498905, "count": 1870, "self": 0.04787880499952735, "children": { "env_step": { "total": 63.30034784998952, "count": 1870, "self": 50.374916936006684, "children": { "SubprocessEnvManager._take_step": { "total": 12.882338780990722, "count": 1870, "self": 0.2439319729824092, "children": { "TorchPolicy.evaluate": { "total": 12.638406808008313, "count": 1870, "self": 2.2907138280179424, "children": { "TorchPolicy.sample_actions": { "total": 10.34769297999037, "count": 1870, "self": 10.34769297999037 } } } } }, "workers": { "total": 0.043092132992114784, "count": 1870, "self": 0.0, "children": { "worker_root": { "total": 67.45999299600635, "count": 1870, "is_parallel": true, "self": 31.84322360999795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003367625000009866, "count": 1, "is_parallel": true, "self": 0.0012066419999428035, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021609830000670627, "count": 10, "is_parallel": true, "self": 0.0021609830000670627 } } }, "UnityEnvironment.step": { "total": 0.06487793099995542, "count": 1, "is_parallel": true, "self": 0.0007052249998196203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042755599997690297, "count": 1, "is_parallel": true, "self": 0.00042755599997690297 }, "communicator.exchange": { "total": 0.06134676700003183, "count": 1, "is_parallel": true, "self": 0.06134676700003183 }, "steps_from_proto": { "total": 0.002398383000127069, "count": 1, "is_parallel": true, "self": 0.0005092559995318879, "children": { "_process_rank_one_or_two_observation": { "total": 0.001889127000595181, "count": 10, "is_parallel": true, "self": 0.001889127000595181 } } } } } } }, "UnityEnvironment.step": { "total": 35.6167693860084, "count": 1869, "is_parallel": true, "self": 1.4157899560318583, "children": { "UnityEnvironment._generate_step_input": { "total": 0.7608470329955708, "count": 1869, "is_parallel": true, "self": 0.7608470329955708 }, "communicator.exchange": { "total": 28.475748135986123, "count": 1869, "is_parallel": true, "self": 28.475748135986123 }, "steps_from_proto": { "total": 4.964384260994848, "count": 1869, "is_parallel": true, "self": 1.1440191470478567, "children": { "_process_rank_one_or_two_observation": { "total": 3.820365113946991, "count": 18690, "is_parallel": true, "self": 3.820365113946991 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004174119999333925, "count": 1, "self": 0.0004174119999333925, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 62.83309614909376, "count": 64812, "is_parallel": true, "self": 1.5768730380386842, "children": { "process_trajectory": { "total": 35.00429760905536, "count": 64812, "is_parallel": true, "self": 35.00429760905536 }, "_update_policy": { "total": 26.25192550199972, "count": 9, "is_parallel": true, "self": 9.302020840993919, "children": { "TorchPPOOptimizer.update": { "total": 16.949904661005803, "count": 456, "is_parallel": true, "self": 16.949904661005803 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1535540449999644, "count": 1, "self": 0.0012907929999528278, "children": { "RLTrainer._checkpoint": { "total": 0.15226325200001156, "count": 1, "self": 0.15226325200001156 } } } } } } }