{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0126169919967651, "min": 1.0126169919967651, "max": 2.8681468963623047, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9690.7451171875, "min": 9690.7451171875, "max": 29530.44140625, "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": 12.421013832092285, "min": 0.2773132026195526, "max": 12.421013832092285, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2422.09765625, "min": 53.79875946044922, "max": 2508.53955078125, "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": 0.07021687779185823, "min": 0.06332163160311444, "max": 0.07454985893826804, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2808675111674329, "min": 0.25328652641245775, "max": 0.36455960471457555, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2171312509214177, "min": 0.09964195125982825, "max": 0.27287196242341805, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8685250036856708, "min": 0.398567805039313, "max": 1.3643598121170903, "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": 24.636363636363637, "min": 2.8636363636363638, "max": 25.072727272727274, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1084.0, "min": 126.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.636363636363637, "min": 2.8636363636363638, "max": 25.072727272727274, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1084.0, "min": 126.0, "max": 1379.0, "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": "1693418396", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/yaohua/miniconda3/envs/drl/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0.dev20230830", "numpy_version": "1.21.2", "end_time_seconds": "1693418566" }, "total": 170.3565218399999, "count": 1, "self": 0.1668417320001936, "children": { "run_training.setup": { "total": 0.009950920999926893, "count": 1, "self": 0.009950920999926893 }, "TrainerController.start_learning": { "total": 170.1797291869998, "count": 1, "self": 0.2891348690354789, "children": { "TrainerController._reset_env": { "total": 0.5838983539997571, "count": 1, "self": 0.5838983539997571 }, "TrainerController.advance": { "total": 169.27665021796474, "count": 18203, "self": 0.1311475789539145, "children": { "env_step": { "total": 169.14550263901083, "count": 18203, "self": 132.28178854596217, "children": { "SubprocessEnvManager._take_step": { "total": 36.71902244403827, "count": 18203, "self": 0.7006604129533116, "children": { "TorchPolicy.evaluate": { "total": 36.01836203108496, "count": 18203, "self": 36.01836203108496 } } }, "workers": { "total": 0.14469164901038312, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 169.81880478703897, "count": 18203, "is_parallel": true, "self": 79.29413514805674, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008780729999671166, "count": 1, "is_parallel": true, "self": 0.00022312299961413373, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006549500003529829, "count": 10, "is_parallel": true, "self": 0.0006549500003529829 } } }, "UnityEnvironment.step": { "total": 0.013905032999900868, "count": 1, "is_parallel": true, "self": 0.00027716399972632644, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024201499991249875, "count": 1, "is_parallel": true, "self": 0.00024201499991249875 }, "communicator.exchange": { "total": 0.012422164999861707, "count": 1, "is_parallel": true, "self": 0.012422164999861707 }, "steps_from_proto": { "total": 0.0009636890004003362, "count": 1, "is_parallel": true, "self": 0.00022662000083073508, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007370689995696011, "count": 10, "is_parallel": true, "self": 0.0007370689995696011 } } } } } } }, "UnityEnvironment.step": { "total": 90.52466963898223, "count": 18202, "is_parallel": true, "self": 3.9828385068908574, "children": { "UnityEnvironment._generate_step_input": { "total": 2.4486729480631766, "count": 18202, "is_parallel": true, "self": 2.4486729480631766 }, "communicator.exchange": { "total": 71.54483532201311, "count": 18202, "is_parallel": true, "self": 71.54483532201311 }, "steps_from_proto": { "total": 12.548322862015084, "count": 18202, "is_parallel": true, "self": 2.6262885749561065, "children": { "_process_rank_one_or_two_observation": { "total": 9.922034287058977, "count": 182020, "is_parallel": true, "self": 9.922034287058977 } } } } } } } } } } } } }, "trainer_threads": { "total": 7.560699987152475e-05, "count": 1, "self": 7.560699987152475e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 169.15595792605836, "count": 95202, "is_parallel": true, "self": 0.9902447380063677, "children": { "process_trajectory": { "total": 93.98189231205197, "count": 95202, "is_parallel": true, "self": 93.624514553052, "children": { "RLTrainer._checkpoint": { "total": 0.3573777589999736, "count": 4, "is_parallel": true, "self": 0.3573777589999736 } } }, "_update_policy": { "total": 74.18382087600003, "count": 90, "is_parallel": true, "self": 19.958428251011355, "children": { "TorchPPOOptimizer.update": { "total": 54.22539262498867, "count": 4587, "is_parallel": true, "self": 54.22539262498867 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02997013899994272, "count": 1, "self": 0.00043325500018909224, "children": { "RLTrainer._checkpoint": { "total": 0.029536883999753627, "count": 1, "self": 0.029536883999753627 } } } } } } }