{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0357815027236938, "min": 1.0357815027236938, "max": 2.8705270290374756, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9935.2158203125, "min": 9935.2158203125, "max": 29554.947265625, "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": 12.822433471679688, "min": 0.27213868498802185, "max": 12.822433471679688, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.37451171875, "min": 52.79490280151367, "max": 2594.848388671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07289169276790584, "min": 0.06298823175340088, "max": 0.07757223419794887, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2915667710716234, "min": 0.2634797156862595, "max": 0.3878611709897443, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22037151492401666, "min": 0.11214016662344482, "max": 0.26953145328397843, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8814860596960666, "min": 0.4485606664937793, "max": 1.3248890492261625, "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": 25.227272727272727, "min": 2.772727272727273, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 122.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 2.772727272727273, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 122.0, "max": 1404.0, "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": "1678272959", "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=SnowballTarget1 --no-graphics", "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": "1678273408" }, "total": 448.257835743, "count": 1, "self": 0.3914250429999697, "children": { "run_training.setup": { "total": 0.11714831399996228, "count": 1, "self": 0.11714831399996228 }, "TrainerController.start_learning": { "total": 447.74926238600005, "count": 1, "self": 0.5200912450023907, "children": { "TrainerController._reset_env": { "total": 8.965633346999994, "count": 1, "self": 8.965633346999994 }, "TrainerController.advance": { "total": 438.15074433299765, "count": 18213, "self": 0.25321442699851104, "children": { "env_step": { "total": 437.89752990599914, "count": 18213, "self": 300.869113708991, "children": { "SubprocessEnvManager._take_step": { "total": 136.77417483200475, "count": 18213, "self": 1.6389601640049705, "children": { "TorchPolicy.evaluate": { "total": 135.13521466799978, "count": 18213, "self": 29.66688438100516, "children": { "TorchPolicy.sample_actions": { "total": 105.46833028699461, "count": 18213, "self": 105.46833028699461 } } } } }, "workers": { "total": 0.254241365003395, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 446.3550284099972, "count": 18213, "is_parallel": true, "self": 218.0678625389885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004371280999976079, "count": 1, "is_parallel": true, "self": 0.0028215730000056283, "children": { "_process_rank_one_or_two_observation": { "total": 0.001549707999970451, "count": 10, "is_parallel": true, "self": 0.001549707999970451 } } }, "UnityEnvironment.step": { "total": 0.033972428000026866, "count": 1, "is_parallel": true, "self": 0.0005469659999448595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003275050000297597, "count": 1, "is_parallel": true, "self": 0.0003275050000297597 }, "communicator.exchange": { "total": 0.03136680800002978, "count": 1, "is_parallel": true, "self": 0.03136680800002978 }, "steps_from_proto": { "total": 0.0017311490000224694, "count": 1, "is_parallel": true, "self": 0.0004044029999477061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013267460000747633, "count": 10, "is_parallel": true, "self": 0.0013267460000747633 } } } } } } }, "UnityEnvironment.step": { "total": 228.2871658710087, "count": 18212, "is_parallel": true, "self": 9.235815920003176, "children": { "UnityEnvironment._generate_step_input": { "total": 5.061000656000715, "count": 18212, "is_parallel": true, "self": 5.061000656000715 }, "communicator.exchange": { "total": 184.0724910280041, "count": 18212, "is_parallel": true, "self": 184.0724910280041 }, "steps_from_proto": { "total": 29.917858267000724, "count": 18212, "is_parallel": true, "self": 6.422078113976227, "children": { "_process_rank_one_or_two_observation": { "total": 23.495780153024498, "count": 182120, "is_parallel": true, "self": 23.495780153024498 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012160699998275959, "count": 1, "self": 0.00012160699998275959, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 434.8596011100141, "count": 398896, "is_parallel": true, "self": 9.899635260021341, "children": { "process_trajectory": { "total": 250.2685738619923, "count": 398896, "is_parallel": true, "self": 249.3590519109921, "children": { "RLTrainer._checkpoint": { "total": 0.9095219510002153, "count": 4, "is_parallel": true, "self": 0.9095219510002153 } } }, "_update_policy": { "total": 174.69139198800048, "count": 90, "is_parallel": true, "self": 62.47412399899952, "children": { "TorchPPOOptimizer.update": { "total": 112.21726798900096, "count": 4587, "is_parallel": true, "self": 112.21726798900096 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1126718540000411, "count": 1, "self": 0.0009363580001036098, "children": { "RLTrainer._checkpoint": { "total": 0.11173549599993748, "count": 1, "self": 0.11173549599993748 } } } } } } }