{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9801653623580933, "min": 0.9801653623580933, "max": 2.8615078926086426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9347.8369140625, "min": 9347.8369140625, "max": 29304.703125, "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": 12.736773490905762, "min": 0.34319406747817993, "max": 12.736773490905762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2483.6708984375, "min": 66.57965087890625, "max": 2579.882568359375, "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": 0.07201830230798234, "min": 0.06227893507600005, "max": 0.0740372302772063, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28807320923192936, "min": 0.2491157403040002, "max": 0.37006487793234344, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2302800060487261, "min": 0.11092854301244312, "max": 0.28594827768849396, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9211200241949044, "min": 0.4437141720497725, "max": 1.365790002486285, "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": 24.568181818181817, "min": 3.3636363636363638, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 148.0, "max": 1416.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.568181818181817, "min": 3.3636363636363638, "max": 25.745454545454546, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 148.0, "max": 1416.0, "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": "1689924632", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1689925145" }, "total": 512.884346764, "count": 1, "self": 0.43255971699989004, "children": { "run_training.setup": { "total": 0.035975317999998424, "count": 1, "self": 0.035975317999998424 }, "TrainerController.start_learning": { "total": 512.4158117290001, "count": 1, "self": 0.5948712290037861, "children": { "TrainerController._reset_env": { "total": 6.575547456999971, "count": 1, "self": 6.575547456999971 }, "TrainerController.advance": { "total": 505.07646091999646, "count": 18201, "self": 0.31200571998851956, "children": { "env_step": { "total": 504.76445520000794, "count": 18201, "self": 369.37042571002047, "children": { "SubprocessEnvManager._take_step": { "total": 135.07660992899378, "count": 18201, "self": 1.860584933997643, "children": { "TorchPolicy.evaluate": { "total": 133.21602499499613, "count": 18201, "self": 133.21602499499613 } } }, "workers": { "total": 0.3174195609936987, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 510.6022933299943, "count": 18201, "is_parallel": true, "self": 240.45676255298577, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.013014320000024782, "count": 1, "is_parallel": true, "self": 0.011336735000099907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016775849999248749, "count": 10, "is_parallel": true, "self": 0.0016775849999248749 } } }, "UnityEnvironment.step": { "total": 0.03892761699995617, "count": 1, "is_parallel": true, "self": 0.0004898130000015044, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045132599996122735, "count": 1, "is_parallel": true, "self": 0.00045132599996122735 }, "communicator.exchange": { "total": 0.03561491400000705, "count": 1, "is_parallel": true, "self": 0.03561491400000705 }, "steps_from_proto": { "total": 0.0023715639999863924, "count": 1, "is_parallel": true, "self": 0.00041039100000261897, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019611729999837735, "count": 10, "is_parallel": true, "self": 0.0019611729999837735 } } } } } } }, "UnityEnvironment.step": { "total": 270.14553077700856, "count": 18200, "is_parallel": true, "self": 11.307711478000044, "children": { "UnityEnvironment._generate_step_input": { "total": 5.782906792004951, "count": 18200, "is_parallel": true, "self": 5.782906792004951 }, "communicator.exchange": { "total": 214.0798345230013, "count": 18200, "is_parallel": true, "self": 214.0798345230013 }, "steps_from_proto": { "total": 38.97507798400227, "count": 18200, "is_parallel": true, "self": 7.456057905014859, "children": { "_process_rank_one_or_two_observation": { "total": 31.51902007898741, "count": 182000, "is_parallel": true, "self": 31.51902007898741 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012452199996459967, "count": 1, "self": 0.00012452199996459967, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 500.9937322460283, "count": 473951, "is_parallel": true, "self": 10.952340157010156, "children": { "process_trajectory": { "total": 275.88385727001776, "count": 473951, "is_parallel": true, "self": 275.0018720660177, "children": { "RLTrainer._checkpoint": { "total": 0.8819852040000455, "count": 4, "is_parallel": true, "self": 0.8819852040000455 } } }, "_update_policy": { "total": 214.15753481900038, "count": 90, "is_parallel": true, "self": 84.60799826900353, "children": { "TorchPPOOptimizer.update": { "total": 129.54953654999684, "count": 4587, "is_parallel": true, "self": 129.54953654999684 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1688076009999122, "count": 1, "self": 0.0008590369999410541, "children": { "RLTrainer._checkpoint": { "total": 0.16794856399997116, "count": 1, "self": 0.16794856399997116 } } } } } } }