{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0270254611968994, "min": 1.0270254611968994, "max": 2.8643999099731445, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9817.3359375, "min": 9817.3359375, "max": 29523.37109375, "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": 12.82081127166748, "min": 0.37841013073921204, "max": 12.82081127166748, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2500.05810546875, "min": 73.41156768798828, "max": 2607.163330078125, "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": 0.06854818476416519, "min": 0.0643163375725956, "max": 0.07436987840828449, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27419273905666075, "min": 0.25978066855995896, "max": 0.3663731368929696, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.227524418164702, "min": 0.16221944419393206, "max": 0.3004073198519501, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.910097672658808, "min": 0.6488777767757282, "max": 1.5020365992597506, "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": 24.977272727272727, "min": 3.8181818181818183, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 168.0, "max": 1396.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 3.8181818181818183, "max": 25.381818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 168.0, "max": 1396.0, "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": "1679167394", "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": "1679167847" }, "total": 453.7898775939998, "count": 1, "self": 0.4354834020000453, "children": { "run_training.setup": { "total": 0.1047147459998996, "count": 1, "self": 0.1047147459998996 }, "TrainerController.start_learning": { "total": 453.24967944599985, "count": 1, "self": 0.5638473929893735, "children": { "TrainerController._reset_env": { "total": 9.133020522000152, "count": 1, "self": 9.133020522000152 }, "TrainerController.advance": { "total": 443.42588098601027, "count": 18201, "self": 0.2721322380125457, "children": { "env_step": { "total": 443.1537487479977, "count": 18201, "self": 322.64024140996526, "children": { "SubprocessEnvManager._take_step": { "total": 120.25271540700214, "count": 18201, "self": 2.1309301779597263, "children": { "TorchPolicy.evaluate": { "total": 118.12178522904242, "count": 18201, "self": 118.12178522904242 } } }, "workers": { "total": 0.26079193103032594, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 451.82944479100297, "count": 18201, "is_parallel": true, "self": 215.69019561603636, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006535511000038241, "count": 1, "is_parallel": true, "self": 0.0049781130005612795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015573979994769616, "count": 10, "is_parallel": true, "self": 0.0015573979994769616 } } }, "UnityEnvironment.step": { "total": 0.04446695400019962, "count": 1, "is_parallel": true, "self": 0.0005268940003588796, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003831980002360069, "count": 1, "is_parallel": true, "self": 0.0003831980002360069 }, "communicator.exchange": { "total": 0.041805258999829675, "count": 1, "is_parallel": true, "self": 0.041805258999829675 }, "steps_from_proto": { "total": 0.0017516029997750593, "count": 1, "is_parallel": true, "self": 0.0003680039990285877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013835990007464716, "count": 10, "is_parallel": true, "self": 0.0013835990007464716 } } } } } } }, "UnityEnvironment.step": { "total": 236.1392491749666, "count": 18200, "is_parallel": true, "self": 9.203442108927447, "children": { "UnityEnvironment._generate_step_input": { "total": 4.976952736002659, "count": 18200, "is_parallel": true, "self": 4.976952736002659 }, "communicator.exchange": { "total": 191.95092109205598, "count": 18200, "is_parallel": true, "self": 191.95092109205598 }, "steps_from_proto": { "total": 30.007933237980524, "count": 18200, "is_parallel": true, "self": 5.974468635939957, "children": { "_process_rank_one_or_two_observation": { "total": 24.033464602040567, "count": 182000, "is_parallel": true, "self": 24.033464602040567 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014397399991139537, "count": 1, "self": 0.00014397399991139537, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 440.4094870261001, "count": 379918, "is_parallel": true, "self": 9.09585702595814, "children": { "process_trajectory": { "total": 242.07077342314187, "count": 379918, "is_parallel": true, "self": 240.55411894014242, "children": { "RLTrainer._checkpoint": { "total": 1.5166544829994564, "count": 4, "is_parallel": true, "self": 1.5166544829994564 } } }, "_update_policy": { "total": 189.2428565770001, "count": 90, "is_parallel": true, "self": 71.15556172199285, "children": { "TorchPPOOptimizer.update": { "total": 118.08729485500726, "count": 4584, "is_parallel": true, "self": 118.08729485500726 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1267865710001388, "count": 1, "self": 0.0008416740001848666, "children": { "RLTrainer._checkpoint": { "total": 0.12594489699995393, "count": 1, "self": 0.12594489699995393 } } } } } } }