{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0141199827194214, "min": 1.0141199827194214, "max": 2.875821113586426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9682.8173828125, "min": 9682.8173828125, "max": 29641.087890625, "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": 12.902083396911621, "min": 0.2960631251335144, "max": 12.902083396911621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.90625, "min": 57.436248779296875, "max": 2623.96484375, "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": 0.07049313669674173, "min": 0.0644272622231345, "max": 0.0764252812304881, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2819725467869669, "min": 0.2582959945897992, "max": 0.3821264061524405, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23663658363854184, "min": 0.11485266042918918, "max": 0.29705087716380757, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9465463345541674, "min": 0.4594106417167567, "max": 1.4083750101135057, "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": 25.204545454545453, "min": 3.0, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1109.0, "min": 132.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.204545454545453, "min": 3.0, "max": 25.672727272727272, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1109.0, "min": 132.0, "max": 1412.0, "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": "1685311683", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685312150" }, "total": 467.7114481809999, "count": 1, "self": 0.4385438670001349, "children": { "run_training.setup": { "total": 0.07155201999989913, "count": 1, "self": 0.07155201999989913 }, "TrainerController.start_learning": { "total": 467.2013522939999, "count": 1, "self": 0.5257022050368505, "children": { "TrainerController._reset_env": { "total": 4.201717169999938, "count": 1, "self": 4.201717169999938 }, "TrainerController.advance": { "total": 462.33562029496284, "count": 18202, "self": 0.24922935798485923, "children": { "env_step": { "total": 462.086390936978, "count": 18202, "self": 341.50952459996006, "children": { "SubprocessEnvManager._take_step": { "total": 120.316995179983, "count": 18202, "self": 1.7305878369897982, "children": { "TorchPolicy.evaluate": { "total": 118.5864073429932, "count": 18202, "self": 118.5864073429932 } } }, "workers": { "total": 0.25987115703492236, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 465.5904122599811, "count": 18202, "is_parallel": true, "self": 219.2487712550178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00501523800016912, "count": 1, "is_parallel": true, "self": 0.0035218989996792516, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014933390004898683, "count": 10, "is_parallel": true, "self": 0.0014933390004898683 } } }, "UnityEnvironment.step": { "total": 0.03605091399981575, "count": 1, "is_parallel": true, "self": 0.0006088399998134264, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003551679999418411, "count": 1, "is_parallel": true, "self": 0.0003551679999418411 }, "communicator.exchange": { "total": 0.03309566600000835, "count": 1, "is_parallel": true, "self": 0.03309566600000835 }, "steps_from_proto": { "total": 0.00199124000005213, "count": 1, "is_parallel": true, "self": 0.0003856970004108007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016055429996413295, "count": 10, "is_parallel": true, "self": 0.0016055429996413295 } } } } } } }, "UnityEnvironment.step": { "total": 246.34164100496332, "count": 18201, "is_parallel": true, "self": 9.806160137978395, "children": { "UnityEnvironment._generate_step_input": { "total": 5.299839410998857, "count": 18201, "is_parallel": true, "self": 5.299839410998857 }, "communicator.exchange": { "total": 197.98630080398698, "count": 18201, "is_parallel": true, "self": 197.98630080398698 }, "steps_from_proto": { "total": 33.24934065199909, "count": 18201, "is_parallel": true, "self": 6.270182520021308, "children": { "_process_rank_one_or_two_observation": { "total": 26.979158131977783, "count": 182010, "is_parallel": true, "self": 26.979158131977783 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001498289998380642, "count": 1, "self": 0.0001498289998380642, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 459.01784315200234, "count": 415378, "is_parallel": true, "self": 9.26491669492384, "children": { "process_trajectory": { "total": 249.22528830307783, "count": 415378, "is_parallel": true, "self": 247.46492083607745, "children": { "RLTrainer._checkpoint": { "total": 1.7603674670003784, "count": 4, "is_parallel": true, "self": 1.7603674670003784 } } }, "_update_policy": { "total": 200.52763815400067, "count": 90, "is_parallel": true, "self": 79.23621742298837, "children": { "TorchPPOOptimizer.update": { "total": 121.2914207310123, "count": 4584, "is_parallel": true, "self": 121.2914207310123 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13816279500042583, "count": 1, "self": 0.0009179570006381255, "children": { "RLTrainer._checkpoint": { "total": 0.1372448379997877, "count": 1, "self": 0.1372448379997877 } } } } } } }