{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9174408912658691, "min": 0.9174408912658691, "max": 2.871260404586792, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8769.8173828125, "min": 8769.8173828125, "max": 29562.49609375, "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": 12.863314628601074, "min": 0.43707671761512756, "max": 12.951693534851074, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.346435546875, "min": 84.79288482666016, "max": 2642.1455078125, "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": 0.06438801145493783, "min": 0.0626728032122414, "max": 0.0778766179900427, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25755204581975133, "min": 0.2506912128489656, "max": 0.36207324478720476, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21953009375754526, "min": 0.12916455509405875, "max": 0.28170055275162065, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.878120375030181, "min": 0.516658220376235, "max": 1.3901869727700364, "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": 25.0, "min": 3.522727272727273, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1100.0, "min": 155.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.0, "min": 3.522727272727273, "max": 25.681818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1100.0, "min": 155.0, "max": 1389.0, "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": "1703753127", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703753570" }, "total": 443.0351517739999, "count": 1, "self": 0.6853743639999266, "children": { "run_training.setup": { "total": 0.05105088099992372, "count": 1, "self": 0.05105088099992372 }, "TrainerController.start_learning": { "total": 442.2987265290001, "count": 1, "self": 0.5567954500031647, "children": { "TrainerController._reset_env": { "total": 3.6712743700001056, "count": 1, "self": 3.6712743700001056 }, "TrainerController.advance": { "total": 437.93323745399664, "count": 18200, "self": 0.2639428719884336, "children": { "env_step": { "total": 437.6692945820082, "count": 18200, "self": 288.47980374201245, "children": { "SubprocessEnvManager._take_step": { "total": 148.90554636900447, "count": 18200, "self": 1.44331982797803, "children": { "TorchPolicy.evaluate": { "total": 147.46222654102644, "count": 18200, "self": 147.46222654102644 } } }, "workers": { "total": 0.28394447099128683, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 441.0513237989901, "count": 18200, "is_parallel": true, "self": 216.75184364299787, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053219110000100045, "count": 1, "is_parallel": true, "self": 0.0034738510001943723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018480599998156322, "count": 10, "is_parallel": true, "self": 0.0018480599998156322 } } }, "UnityEnvironment.step": { "total": 0.03853142100001605, "count": 1, "is_parallel": true, "self": 0.0006347170000253755, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048385299999154086, "count": 1, "is_parallel": true, "self": 0.00048385299999154086 }, "communicator.exchange": { "total": 0.03525317800006178, "count": 1, "is_parallel": true, "self": 0.03525317800006178 }, "steps_from_proto": { "total": 0.0021596729999373565, "count": 1, "is_parallel": true, "self": 0.0004042220001565511, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017554509997808054, "count": 10, "is_parallel": true, "self": 0.0017554509997808054 } } } } } } }, "UnityEnvironment.step": { "total": 224.29948015599223, "count": 18199, "is_parallel": true, "self": 10.58938965198979, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3387402649960904, "count": 18199, "is_parallel": true, "self": 5.3387402649960904 }, "communicator.exchange": { "total": 175.19892281600062, "count": 18199, "is_parallel": true, "self": 175.19892281600062 }, "steps_from_proto": { "total": 33.17242742300573, "count": 18199, "is_parallel": true, "self": 6.153614853954537, "children": { "_process_rank_one_or_two_observation": { "total": 27.018812569051192, "count": 181990, "is_parallel": true, "self": 27.018812569051192 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.707900001856615e-05, "count": 1, "self": 6.707900001856615e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 432.5435580229565, "count": 667924, "is_parallel": true, "self": 13.755920752973452, "children": { "process_trajectory": { "total": 239.2784931809831, "count": 667924, "is_parallel": true, "self": 238.67032206398312, "children": { "RLTrainer._checkpoint": { "total": 0.6081711169999835, "count": 4, "is_parallel": true, "self": 0.6081711169999835 } } }, "_update_policy": { "total": 179.50914408899996, "count": 90, "is_parallel": true, "self": 55.76859408799885, "children": { "TorchPPOOptimizer.update": { "total": 123.74055000100111, "count": 4587, "is_parallel": true, "self": 123.74055000100111 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13735217600014948, "count": 1, "self": 0.0013656970002102753, "children": { "RLTrainer._checkpoint": { "total": 0.1359864789999392, "count": 1, "self": 0.1359864789999392 } } } } } } }