{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9179275035858154, "min": 0.9179275035858154, "max": 2.8735694885253906, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8764.3720703125, "min": 8764.3720703125, "max": 29428.224609375, "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": 12.375489234924316, "min": 0.37875932455062866, "max": 12.375489234924316, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2413.220458984375, "min": 73.47930908203125, "max": 2500.14111328125, "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": 0.06796336355681905, "min": 0.06294213405070717, "max": 0.07791685850579776, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2718534542272762, "min": 0.25543304471248834, "max": 0.3617314216886263, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2059928269362917, "min": 0.1557449033260163, "max": 0.2744271019656284, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8239713077451668, "min": 0.6229796133040651, "max": 1.3563206920436783, "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": 24.318181818181817, "min": 3.9318181818181817, "max": 24.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1070.0, "min": 173.0, "max": 1345.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.318181818181817, "min": 3.9318181818181817, "max": 24.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1070.0, "min": 173.0, "max": 1345.0, "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": "1681759964", "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": "1681760405" }, "total": 440.46859428199997, "count": 1, "self": 0.4359512349999477, "children": { "run_training.setup": { "total": 0.17141490300002715, "count": 1, "self": 0.17141490300002715 }, "TrainerController.start_learning": { "total": 439.861228144, "count": 1, "self": 0.5152376380012811, "children": { "TrainerController._reset_env": { "total": 4.6106560800000125, "count": 1, "self": 4.6106560800000125 }, "TrainerController.advance": { "total": 434.60440921199864, "count": 18202, "self": 0.2631542980001882, "children": { "env_step": { "total": 434.34125491399845, "count": 18202, "self": 316.90044152399935, "children": { "SubprocessEnvManager._take_step": { "total": 117.18193427999881, "count": 18202, "self": 1.6607725389928873, "children": { "TorchPolicy.evaluate": { "total": 115.52116174100593, "count": 18202, "self": 115.52116174100593 } } }, "workers": { "total": 0.2588791100002936, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 438.4179548940005, "count": 18202, "is_parallel": true, "self": 203.9495121160038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006648054999971009, "count": 1, "is_parallel": true, "self": 0.0045192789999646266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021287760000063827, "count": 10, "is_parallel": true, "self": 0.0021287760000063827 } } }, "UnityEnvironment.step": { "total": 0.03414599699999599, "count": 1, "is_parallel": true, "self": 0.0005532200000288867, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003199849999759863, "count": 1, "is_parallel": true, "self": 0.0003199849999759863 }, "communicator.exchange": { "total": 0.03149435199998152, "count": 1, "is_parallel": true, "self": 0.03149435199998152 }, "steps_from_proto": { "total": 0.0017784400000095957, "count": 1, "is_parallel": true, "self": 0.00036024399997813816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014181960000314575, "count": 10, "is_parallel": true, "self": 0.0014181960000314575 } } } } } } }, "UnityEnvironment.step": { "total": 234.4684427779967, "count": 18201, "is_parallel": true, "self": 9.485390414988842, "children": { "UnityEnvironment._generate_step_input": { "total": 5.328566381997575, "count": 18201, "is_parallel": true, "self": 5.328566381997575 }, "communicator.exchange": { "total": 189.68398334500796, "count": 18201, "is_parallel": true, "self": 189.68398334500796 }, "steps_from_proto": { "total": 29.970502636002323, "count": 18201, "is_parallel": true, "self": 5.791239456007588, "children": { "_process_rank_one_or_two_observation": { "total": 24.179263179994734, "count": 182010, "is_parallel": true, "self": 24.179263179994734 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011240200001338962, "count": 1, "self": 0.00011240200001338962, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.3469909450287, "count": 383937, "is_parallel": true, "self": 9.209736839993695, "children": { "process_trajectory": { "total": 237.88822716803503, "count": 383937, "is_parallel": true, "self": 236.74090831303494, "children": { "RLTrainer._checkpoint": { "total": 1.1473188550000941, "count": 4, "is_parallel": true, "self": 1.1473188550000941 } } }, "_update_policy": { "total": 184.249026937, "count": 90, "is_parallel": true, "self": 66.5340645410019, "children": { "TorchPPOOptimizer.update": { "total": 117.7149623959981, "count": 4587, "is_parallel": true, "self": 117.7149623959981 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1308128120000447, "count": 1, "self": 0.000869348000037462, "children": { "RLTrainer._checkpoint": { "total": 0.12994346400000722, "count": 1, "self": 0.12994346400000722 } } } } } } }