{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.551633894443512, "min": 0.551633894443512, "max": 2.87612247467041, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5285.2041015625, "min": 5285.2041015625, "max": 29454.37109375, "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": 6.534955978393555, "min": 0.3020043969154358, "max": 6.543118476867676, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1274.31640625, "min": 58.58885192871094, "max": 1334.796142578125, "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": 0.04307588564036753, "min": 0.04008093812080915, "max": 0.056019695724777795, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.17230354256147012, "min": 0.1603237524832366, "max": 0.280098478623889, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18188842882712683, "min": 0.09557582406948009, "max": 0.22587015867854157, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7275537153085073, "min": 0.38230329627792037, "max": 1.1109948214143515, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10538800000000001, "min": 0.10538800000000001, "max": 0.29458799999999996, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.42155200000000004, "min": 0.42155200000000004, "max": 1.4234400000000003, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.34090909090909, "min": 3.1363636363636362, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1115.0, "min": 138.0, "max": 1445.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.34090909090909, "min": 3.1363636363636362, "max": 26.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1115.0, "min": 138.0, "max": 1445.0, "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": "1694619719", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1694620201" }, "total": 481.80152665799994, "count": 1, "self": 0.4361083459998554, "children": { "run_training.setup": { "total": 0.04833306800003356, "count": 1, "self": 0.04833306800003356 }, "TrainerController.start_learning": { "total": 481.31708524400005, "count": 1, "self": 0.652727274994163, "children": { "TrainerController._reset_env": { "total": 4.547186316999955, "count": 1, "self": 4.547186316999955 }, "TrainerController.advance": { "total": 475.9679630390059, "count": 18203, "self": 0.3170525110105018, "children": { "env_step": { "total": 475.6509105279954, "count": 18203, "self": 328.5580304680004, "children": { "SubprocessEnvManager._take_step": { "total": 146.7157508660008, "count": 18203, "self": 1.8878255010083649, "children": { "TorchPolicy.evaluate": { "total": 144.82792536499244, "count": 18203, "self": 144.82792536499244 } } }, "workers": { "total": 0.3771291939941648, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 479.33830299200247, "count": 18203, "is_parallel": true, "self": 210.98776257599854, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006419024000024365, "count": 1, "is_parallel": true, "self": 0.00487385299993548, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015451710000888852, "count": 10, "is_parallel": true, "self": 0.0015451710000888852 } } }, "UnityEnvironment.step": { "total": 0.05322456700002931, "count": 1, "is_parallel": true, "self": 0.0005348229999526666, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039976999994451035, "count": 1, "is_parallel": true, "self": 0.00039976999994451035 }, "communicator.exchange": { "total": 0.04928013100004591, "count": 1, "is_parallel": true, "self": 0.04928013100004591 }, "steps_from_proto": { "total": 0.003009843000086221, "count": 1, "is_parallel": true, "self": 0.00038720000009107025, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026226429999951506, "count": 10, "is_parallel": true, "self": 0.0026226429999951506 } } } } } } }, "UnityEnvironment.step": { "total": 268.3505404160039, "count": 18202, "is_parallel": true, "self": 11.28629039897919, "children": { "UnityEnvironment._generate_step_input": { "total": 5.62784425601285, "count": 18202, "is_parallel": true, "self": 5.62784425601285 }, "communicator.exchange": { "total": 213.28079224101316, "count": 18202, "is_parallel": true, "self": 213.28079224101316 }, "steps_from_proto": { "total": 38.155613519998724, "count": 18202, "is_parallel": true, "self": 7.095911925979749, "children": { "_process_rank_one_or_two_observation": { "total": 31.059701594018975, "count": 182020, "is_parallel": true, "self": 31.059701594018975 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016669600006480323, "count": 1, "self": 0.00016669600006480323, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.1064159910163, "count": 480781, "is_parallel": true, "self": 10.919858114996941, "children": { "process_trajectory": { "total": 278.2804770060193, "count": 480781, "is_parallel": true, "self": 277.45892816101946, "children": { "RLTrainer._checkpoint": { "total": 0.8215488449998247, "count": 4, "is_parallel": true, "self": 0.8215488449998247 } } }, "_update_policy": { "total": 182.9060808700001, "count": 90, "is_parallel": true, "self": 85.28873336500112, "children": { "TorchPPOOptimizer.update": { "total": 97.61734750499897, "count": 2160, "is_parallel": true, "self": 97.61734750499897 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14904191699997682, "count": 1, "self": 0.0009045499999729145, "children": { "RLTrainer._checkpoint": { "total": 0.1481373670000039, "count": 1, "self": 0.1481373670000039 } } } } } } }