{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5873121023178101, "min": 0.5873121023178101, "max": 2.8776166439056396, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6001.7421875, "min": 5743.4130859375, "max": 29596.287109375, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.320497512817383, "min": 0.3165181279182434, "max": 13.346643447875977, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2597.4970703125, "min": 61.404518127441406, "max": 2730.20263671875, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.04042731446800948, "min": 0.03864792560045771, "max": 0.0543256036387902, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.1617092578720379, "min": 0.15459170240183084, "max": 0.271628018193951, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17447406332939863, "min": 0.10754449265853812, "max": 0.2994558504472176, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6978962533175945, "min": 0.4301779706341525, "max": 1.497279252236088, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.311287896239998e-05, "min": 6.311287896239998e-05, "max": 0.00029675280108239997, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0002524515158495999, "min": 0.0002524515158495999, "max": 0.001454064015312, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12103760000000001, "min": 0.12103760000000001, "max": 0.19891760000000003, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.48415040000000004, "min": 0.48415040000000004, "max": 0.984688, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00105977624, "min": 0.00105977624, "max": 0.00494598824, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00423910496, "min": 0.00423910496, "max": 0.0242359312, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.386363636363637, "min": 3.0681818181818183, "max": 26.386363636363637, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1161.0, "min": 135.0, "max": 1441.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.386363636363637, "min": 3.0681818181818183, "max": 26.386363636363637, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1161.0, "min": 135.0, "max": 1441.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679786025", "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": "1679786925" }, "total": 899.543656866, "count": 1, "self": 0.004955608000045686, "children": { "run_training.setup": { "total": 0.11370095000000902, "count": 1, "self": 0.11370095000000902 }, "TrainerController.start_learning": { "total": 899.425000308, "count": 1, "self": 1.8777937260049384, "children": { "TrainerController._reset_env": { "total": 9.79628939600002, "count": 1, "self": 9.79628939600002 }, "TrainerController.advance": { "total": 887.614315038995, "count": 36798, "self": 0.6274243129998922, "children": { "env_step": { "total": 886.9868907259951, "count": 36798, "self": 612.9160585160167, "children": { "SubprocessEnvManager._take_step": { "total": 273.518237752001, "count": 36798, "self": 4.460513541009789, "children": { "TorchPolicy.evaluate": { "total": 269.05772421099124, "count": 36798, "self": 269.05772421099124 } } }, "workers": { "total": 0.5525944579773068, "count": 36797, "self": 0.0, "children": { "worker_root": { "total": 895.7632007220026, "count": 36797, "is_parallel": true, "self": 404.99374099399586, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006248698000035802, "count": 1, "is_parallel": true, "self": 0.00464364299995168, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016050550000841213, "count": 10, "is_parallel": true, "self": 0.0016050550000841213 } } }, "UnityEnvironment.step": { "total": 0.03538946300000134, "count": 1, "is_parallel": true, "self": 0.0005583369999726528, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024463300002253163, "count": 1, "is_parallel": true, "self": 0.00024463300002253163 }, "communicator.exchange": { "total": 0.03251898600001368, "count": 1, "is_parallel": true, "self": 0.03251898600001368 }, "steps_from_proto": { "total": 0.0020675069999924744, "count": 1, "is_parallel": true, "self": 0.0004112799999802519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016562270000122226, "count": 10, "is_parallel": true, "self": 0.0016562270000122226 } } } } } } }, "UnityEnvironment.step": { "total": 490.7694597280067, "count": 36796, "is_parallel": true, "self": 19.456491647977998, "children": { "UnityEnvironment._generate_step_input": { "total": 10.298666377005475, "count": 36796, "is_parallel": true, "self": 10.298666377005475 }, "communicator.exchange": { "total": 397.0950145830155, "count": 36796, "is_parallel": true, "self": 397.0950145830155 }, "steps_from_proto": { "total": 63.919287120007766, "count": 36796, "is_parallel": true, "self": 12.63411040098481, "children": { "_process_rank_one_or_two_observation": { "total": 51.28517671902296, "count": 367960, "is_parallel": true, "self": 51.28517671902296 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021386999992500932, "count": 1, "self": 0.00021386999992500932, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 881.1373914719685, "count": 841953, "is_parallel": true, "self": 21.111690848929697, "children": { "process_trajectory": { "total": 528.1684591510384, "count": 841953, "is_parallel": true, "self": 525.4359121230385, "children": { "RLTrainer._checkpoint": { "total": 2.7325470279998854, "count": 8, "is_parallel": true, "self": 2.7325470279998854 } } }, "_update_policy": { "total": 331.8572414720004, "count": 184, "is_parallel": true, "self": 152.52067994600662, "children": { "TorchPPOOptimizer.update": { "total": 179.33656152599377, "count": 4416, "is_parallel": true, "self": 179.33656152599377 } } } } } } } } }, "TrainerController._save_models": { "total": 0.136388277000151, "count": 1, "self": 0.0010142660000838077, "children": { "RLTrainer._checkpoint": { "total": 0.13537401100006718, "count": 1, "self": 0.13537401100006718 } } } } } } }