{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.026114821434021, "min": 1.026114821434021, "max": 2.8681693077087402, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9808.6318359375, "min": 9808.6318359375, "max": 29372.921875, "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": 12.59863567352295, "min": 0.4274159073829651, "max": 12.609695434570312, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2456.73388671875, "min": 82.91868591308594, "max": 2556.86962890625, "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": 0.06989119633790859, "min": 0.06238066950851741, "max": 0.0728508560949658, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27956478535163437, "min": 0.25359664498640033, "max": 0.364254280474829, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21823058901902506, "min": 0.12625516106502388, "max": 0.2745835717548342, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8729223560761002, "min": 0.5050206442600955, "max": 1.2931683390748265, "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": 3.477272727272727, "max": 25.12727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 153.0, "max": 1382.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 3.477272727272727, "max": 25.12727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 153.0, "max": 1382.0, "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": "1714415389", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714415844" }, "total": 454.96688982, "count": 1, "self": 0.4400821689998793, "children": { "run_training.setup": { "total": 0.07762357699994027, "count": 1, "self": 0.07762357699994027 }, "TrainerController.start_learning": { "total": 454.4491840740002, "count": 1, "self": 0.5649350209948807, "children": { "TrainerController._reset_env": { "total": 3.250793213999941, "count": 1, "self": 3.250793213999941 }, "TrainerController.advance": { "total": 450.54300560600564, "count": 18199, "self": 0.2872963790139238, "children": { "env_step": { "total": 450.2557092269917, "count": 18199, "self": 293.8344283359738, "children": { "SubprocessEnvManager._take_step": { "total": 156.12787657601143, "count": 18199, "self": 1.4580152889930105, "children": { "TorchPolicy.evaluate": { "total": 154.66986128701842, "count": 18199, "self": 154.66986128701842 } } }, "workers": { "total": 0.29340431500645536, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 453.25480569201954, "count": 18199, "is_parallel": true, "self": 225.85769595102647, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009769147999804773, "count": 1, "is_parallel": true, "self": 0.005242399999360714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0045267480004440586, "count": 10, "is_parallel": true, "self": 0.0045267480004440586 } } }, "UnityEnvironment.step": { "total": 0.041969869000013205, "count": 1, "is_parallel": true, "self": 0.0006880649998493027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004272010000931914, "count": 1, "is_parallel": true, "self": 0.0004272010000931914 }, "communicator.exchange": { "total": 0.03884167399996841, "count": 1, "is_parallel": true, "self": 0.03884167399996841 }, "steps_from_proto": { "total": 0.0020129290001023037, "count": 1, "is_parallel": true, "self": 0.0004067720001330599, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016061569999692438, "count": 10, "is_parallel": true, "self": 0.0016061569999692438 } } } } } } }, "UnityEnvironment.step": { "total": 227.39710974099307, "count": 18198, "is_parallel": true, "self": 10.367211914003747, "children": { "UnityEnvironment._generate_step_input": { "total": 5.284454141006108, "count": 18198, "is_parallel": true, "self": 5.284454141006108 }, "communicator.exchange": { "total": 178.37840468900686, "count": 18198, "is_parallel": true, "self": 178.37840468900686 }, "steps_from_proto": { "total": 33.36703899697636, "count": 18198, "is_parallel": true, "self": 6.313206856961415, "children": { "_process_rank_one_or_two_observation": { "total": 27.053832140014947, "count": 181980, "is_parallel": true, "self": 27.053832140014947 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018504499985283474, "count": 1, "self": 0.00018504499985283474, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.4800992340015, "count": 638214, "is_parallel": true, "self": 13.543267435043845, "children": { "process_trajectory": { "total": 246.48700625495758, "count": 638214, "is_parallel": true, "self": 245.89898512895752, "children": { "RLTrainer._checkpoint": { "total": 0.5880211260000578, "count": 4, "is_parallel": true, "self": 0.5880211260000578 } } }, "_update_policy": { "total": 185.44982554400008, "count": 90, "is_parallel": true, "self": 53.6474246179846, "children": { "TorchPPOOptimizer.update": { "total": 131.80240092601548, "count": 4587, "is_parallel": true, "self": 131.80240092601548 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0902651879998757, "count": 1, "self": 0.0009296909997829061, "children": { "RLTrainer._checkpoint": { "total": 0.0893354970000928, "count": 1, "self": 0.0893354970000928 } } } } } } }