{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8370972275733948, "min": 0.8370972275733948, "max": 2.8588879108428955, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7992.6044921875, "min": 7992.6044921875, "max": 29309.318359375, "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": 12.7811861038208, "min": 0.2791458070278168, "max": 12.972125053405762, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2492.331298828125, "min": 54.15428924560547, "max": 2645.44580078125, "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": 0.06738024796519027, "min": 0.06291451561107761, "max": 0.07693827273871968, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26952099186076106, "min": 0.25165806244431044, "max": 0.3846913636935984, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20532643261785602, "min": 0.12644542183147234, "max": 0.2712783714719847, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8213057304714241, "min": 0.5057816873258894, "max": 1.3563918573599234, "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": 25.113636363636363, "min": 3.477272727272727, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 153.0, "max": 1410.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.477272727272727, "max": 25.636363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 153.0, "max": 1410.0, "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": "1722423914", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722424390" }, "total": 475.9005632330002, "count": 1, "self": 0.43157541400023547, "children": { "run_training.setup": { "total": 0.07085516400002234, "count": 1, "self": 0.07085516400002234 }, "TrainerController.start_learning": { "total": 475.3981326549999, "count": 1, "self": 0.6526122389834654, "children": { "TrainerController._reset_env": { "total": 2.798851610999918, "count": 1, "self": 2.798851610999918 }, "TrainerController.advance": { "total": 471.83864539701653, "count": 18201, "self": 0.3056806940360275, "children": { "env_step": { "total": 471.5329647029805, "count": 18201, "self": 307.6519660479971, "children": { "SubprocessEnvManager._take_step": { "total": 163.5759928999928, "count": 18201, "self": 1.5889170349994401, "children": { "TorchPolicy.evaluate": { "total": 161.98707586499336, "count": 18201, "self": 161.98707586499336 } } }, "workers": { "total": 0.3050057549905887, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 473.9386841219996, "count": 18201, "is_parallel": true, "self": 240.2492969940074, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005626583000093888, "count": 1, "is_parallel": true, "self": 0.003965077000202655, "children": { "_process_rank_one_or_two_observation": { "total": 0.001661505999891233, "count": 10, "is_parallel": true, "self": 0.001661505999891233 } } }, "UnityEnvironment.step": { "total": 0.03818623500001195, "count": 1, "is_parallel": true, "self": 0.0007201499997790961, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003840470001250651, "count": 1, "is_parallel": true, "self": 0.0003840470001250651 }, "communicator.exchange": { "total": 0.03497716600008971, "count": 1, "is_parallel": true, "self": 0.03497716600008971 }, "steps_from_proto": { "total": 0.0021048720000180765, "count": 1, "is_parallel": true, "self": 0.00040893599975788675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016959360002601898, "count": 10, "is_parallel": true, "self": 0.0016959360002601898 } } } } } } }, "UnityEnvironment.step": { "total": 233.68938712799218, "count": 18200, "is_parallel": true, "self": 10.48078469994607, "children": { "UnityEnvironment._generate_step_input": { "total": 5.682723615992472, "count": 18200, "is_parallel": true, "self": 5.682723615992472 }, "communicator.exchange": { "total": 182.06767561701872, "count": 18200, "is_parallel": true, "self": 182.06767561701872 }, "steps_from_proto": { "total": 35.45820319503491, "count": 18200, "is_parallel": true, "self": 6.866202692986008, "children": { "_process_rank_one_or_two_observation": { "total": 28.592000502048904, "count": 182000, "is_parallel": true, "self": 28.592000502048904 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016744699996706913, "count": 1, "self": 0.00016744699996706913, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.90514656193136, "count": 683845, "is_parallel": true, "self": 14.992023835956616, "children": { "process_trajectory": { "total": 259.1903054119739, "count": 683845, "is_parallel": true, "self": 258.483158951974, "children": { "RLTrainer._checkpoint": { "total": 0.7071464599998762, "count": 4, "is_parallel": true, "self": 0.7071464599998762 } } }, "_update_policy": { "total": 191.72281731400085, "count": 90, "is_parallel": true, "self": 61.20790993500623, "children": { "TorchPPOOptimizer.update": { "total": 130.51490737899462, "count": 4587, "is_parallel": true, "self": 130.51490737899462 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10785596100004113, "count": 1, "self": 0.0009831899999426241, "children": { "RLTrainer._checkpoint": { "total": 0.10687277100009851, "count": 1, "self": 0.10687277100009851 } } } } } } }