{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8430759310722351, "min": 0.8374955058097839, "max": 2.8669605255126953, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8058.962890625, "min": 8058.962890625, "max": 29360.54296875, "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": 12.724028587341309, "min": 0.35855093598365784, "max": 12.724028587341309, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2481.185546875, "min": 69.55888366699219, "max": 2590.443603515625, "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": 0.06597507280222249, "min": 0.061843576870730846, "max": 0.07708521172211405, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26390029120888997, "min": 0.24955775643192118, "max": 0.3854260586105702, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20500241066603098, "min": 0.11555116032318706, "max": 0.30802807401792676, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8200096426641239, "min": 0.46220464129274824, "max": 1.3982503238846276, "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": 25.068181818181817, "min": 3.340909090909091, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1103.0, "min": 147.0, "max": 1372.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.068181818181817, "min": 3.340909090909091, "max": 25.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1103.0, "min": 147.0, "max": 1372.0, "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": "1688188451", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688188927" }, "total": 475.8021200469999, "count": 1, "self": 0.43771618199991735, "children": { "run_training.setup": { "total": 0.04449816199996803, "count": 1, "self": 0.04449816199996803 }, "TrainerController.start_learning": { "total": 475.319905703, "count": 1, "self": 0.5445854789983287, "children": { "TrainerController._reset_env": { "total": 5.3552975769999875, "count": 1, "self": 5.3552975769999875 }, "TrainerController.advance": { "total": 469.27876293300153, "count": 18201, "self": 0.2654900440104484, "children": { "env_step": { "total": 469.0132728889911, "count": 18201, "self": 338.76581364398737, "children": { "SubprocessEnvManager._take_step": { "total": 129.98402508500237, "count": 18201, "self": 1.7357756810034743, "children": { "TorchPolicy.evaluate": { "total": 128.2482494039989, "count": 18201, "self": 128.2482494039989 } } }, "workers": { "total": 0.26343416000133857, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 473.6889866560033, "count": 18201, "is_parallel": true, "self": 222.61008176700852, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006142487000033725, "count": 1, "is_parallel": true, "self": 0.0046044930002153706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015379939998183545, "count": 10, "is_parallel": true, "self": 0.0015379939998183545 } } }, "UnityEnvironment.step": { "total": 0.07172585299997536, "count": 1, "is_parallel": true, "self": 0.0008489789998975539, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004511930000035136, "count": 1, "is_parallel": true, "self": 0.0004511930000035136 }, "communicator.exchange": { "total": 0.06806848300004731, "count": 1, "is_parallel": true, "self": 0.06806848300004731 }, "steps_from_proto": { "total": 0.002357198000026983, "count": 1, "is_parallel": true, "self": 0.0004368390001445732, "children": { "_process_rank_one_or_two_observation": { "total": 0.00192035899988241, "count": 10, "is_parallel": true, "self": 0.00192035899988241 } } } } } } }, "UnityEnvironment.step": { "total": 251.07890488899477, "count": 18200, "is_parallel": true, "self": 10.398702379990823, "children": { "UnityEnvironment._generate_step_input": { "total": 5.28655339199679, "count": 18200, "is_parallel": true, "self": 5.28655339199679 }, "communicator.exchange": { "total": 200.4530947470015, "count": 18200, "is_parallel": true, "self": 200.4530947470015 }, "steps_from_proto": { "total": 34.94055437000566, "count": 18200, "is_parallel": true, "self": 6.277371503007544, "children": { "_process_rank_one_or_two_observation": { "total": 28.663182866998113, "count": 182000, "is_parallel": true, "self": 28.663182866998113 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016393500004596717, "count": 1, "self": 0.00016393500004596717, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.674222240988, "count": 453167, "is_parallel": true, "self": 9.962755067050693, "children": { "process_trajectory": { "total": 255.74815967293728, "count": 453167, "is_parallel": true, "self": 254.4720430019371, "children": { "RLTrainer._checkpoint": { "total": 1.2761166710001817, "count": 4, "is_parallel": true, "self": 1.2761166710001817 } } }, "_update_policy": { "total": 199.96330750100003, "count": 90, "is_parallel": true, "self": 75.56816734500171, "children": { "TorchPPOOptimizer.update": { "total": 124.39514015599832, "count": 4587, "is_parallel": true, "self": 124.39514015599832 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14109577900012482, "count": 1, "self": 0.0008497270002862933, "children": { "RLTrainer._checkpoint": { "total": 0.14024605199983853, "count": 1, "self": 0.14024605199983853 } } } } } } }