{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0006494522094727, "min": 1.0006494522094727, "max": 2.8660776615142822, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9576.21484375, "min": 9576.21484375, "max": 29414.5546875, "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": 12.957388877868652, "min": 0.30946454405784607, "max": 12.957388877868652, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.69091796875, "min": 60.0361213684082, "max": 2634.455078125, "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": 0.06534105771268015, "min": 0.05846869440109574, "max": 0.07674659928192805, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2613642308507206, "min": 0.25013603238724447, "max": 0.36477156179784753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19927547353447653, "min": 0.1264968564409726, "max": 0.29178063910381463, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7971018941379061, "min": 0.5059874257638904, "max": 1.4589031955190732, "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": 25.431818181818183, "min": 3.7954545454545454, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1119.0, "min": 167.0, "max": 1402.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.431818181818183, "min": 3.7954545454545454, "max": 25.490909090909092, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1119.0, "min": 167.0, "max": 1402.0, "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": "1718372535", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718372906" }, "total": 370.81312958700005, "count": 1, "self": 0.321463126000026, "children": { "run_training.setup": { "total": 0.06420378300003904, "count": 1, "self": 0.06420378300003904 }, "TrainerController.start_learning": { "total": 370.427462678, "count": 1, "self": 0.47481236900887325, "children": { "TrainerController._reset_env": { "total": 2.8231510009999283, "count": 1, "self": 2.8231510009999283 }, "TrainerController.advance": { "total": 367.0463906389914, "count": 18204, "self": 0.2319738999715355, "children": { "env_step": { "total": 366.81441673901986, "count": 18204, "self": 246.53653117502472, "children": { "SubprocessEnvManager._take_step": { "total": 120.05705593099754, "count": 18204, "self": 1.4692375929970467, "children": { "TorchPolicy.evaluate": { "total": 118.58781833800049, "count": 18204, "self": 118.58781833800049 } } }, "workers": { "total": 0.2208296329976065, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 369.79387144298744, "count": 18204, "is_parallel": true, "self": 188.78822918998526, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0027698799999598123, "count": 1, "is_parallel": true, "self": 0.0007454709999592524, "children": { "_process_rank_one_or_two_observation": { "total": 0.00202440900000056, "count": 10, "is_parallel": true, "self": 0.00202440900000056 } } }, "UnityEnvironment.step": { "total": 0.025320625000063046, "count": 1, "is_parallel": true, "self": 0.0004385660000707503, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002650520000315737, "count": 1, "is_parallel": true, "self": 0.0002650520000315737 }, "communicator.exchange": { "total": 0.023389704999999594, "count": 1, "is_parallel": true, "self": 0.023389704999999594 }, "steps_from_proto": { "total": 0.0012273019999611279, "count": 1, "is_parallel": true, "self": 0.0002824789999067434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009448230000543845, "count": 10, "is_parallel": true, "self": 0.0009448230000543845 } } } } } } }, "UnityEnvironment.step": { "total": 181.00564225300218, "count": 18203, "is_parallel": true, "self": 7.343245973991884, "children": { "UnityEnvironment._generate_step_input": { "total": 3.8959148759977325, "count": 18203, "is_parallel": true, "self": 3.8959148759977325 }, "communicator.exchange": { "total": 145.7570586270026, "count": 18203, "is_parallel": true, "self": 145.7570586270026 }, "steps_from_proto": { "total": 24.009422776009956, "count": 18203, "is_parallel": true, "self": 4.639706014968169, "children": { "_process_rank_one_or_two_observation": { "total": 19.369716761041786, "count": 182030, "is_parallel": true, "self": 19.369716761041786 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014521799994327012, "count": 1, "self": 0.00014521799994327012, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 365.7116739430488, "count": 272810, "is_parallel": true, "self": 4.329317134030589, "children": { "process_trajectory": { "total": 205.89144069901772, "count": 272810, "is_parallel": true, "self": 205.22297689501738, "children": { "RLTrainer._checkpoint": { "total": 0.6684638040003392, "count": 4, "is_parallel": true, "self": 0.6684638040003392 } } }, "_update_policy": { "total": 155.4909161100005, "count": 90, "is_parallel": true, "self": 35.40367433000472, "children": { "TorchPPOOptimizer.update": { "total": 120.0872417799958, "count": 4587, "is_parallel": true, "self": 120.0872417799958 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08296345099984137, "count": 1, "self": 0.0008961079997789057, "children": { "RLTrainer._checkpoint": { "total": 0.08206734300006246, "count": 1, "self": 0.08206734300006246 } } } } } } }