{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.128235101699829, "min": 1.128235101699829, "max": 2.864258050918579, "count": 15 }, "SnowballTarget.Policy.Entropy.sum": { "value": 11579.0771484375, "min": 10804.333984375, "max": 29364.373046875, "count": 15 }, "SnowballTarget.Step.mean": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Step.sum": { "value": 149984.0, "min": 9952.0, "max": 149984.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 6.331068515777588, "min": 0.234155535697937, "max": 6.340497970581055, "count": 15 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1297.8690185546875, "min": 45.42617416381836, "max": 1297.8690185546875, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 15 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.09506043500607084, "min": 0.09171588777578162, "max": 0.1080135574418248, "count": 15 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.4753021750303542, "min": 0.37274642952416676, "max": 0.540067787209124, "count": 15 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1781811682763053, "min": 0.09763798380239612, "max": 0.24721918678751176, "count": 15 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8909058413815265, "min": 0.3905519352095845, "max": 1.2019611543007924, "count": 15 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.776096741333334e-06, "min": 9.776096741333334e-06, "max": 0.00028917600360799995, "count": 15 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.8880483706666666e-05, "min": 4.8880483706666666e-05, "max": 0.0013468800510399999, "count": 15 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10325866666666668, "min": 0.10325866666666668, "max": 0.196392, "count": 15 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5162933333333334, "min": 0.4394346666666667, "max": 0.9489599999999999, "count": 15 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00017260746666666673, "min": 0.00017260746666666673, "max": 0.0048199608, "count": 15 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008630373333333337, "min": 0.0008630373333333337, "max": 0.022453104000000005, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.490909090909092, "min": 3.4545454545454546, "max": 24.8, "count": 15 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1347.0, "min": 152.0, "max": 1364.0, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.490909090909092, "min": 3.4545454545454546, "max": 24.8, "count": 15 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1347.0, "min": 152.0, "max": 1364.0, "count": 15 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 15 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1699070737", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699071149" }, "total": 411.55971185299995, "count": 1, "self": 0.43261215299980904, "children": { "run_training.setup": { "total": 0.041944155999999566, "count": 1, "self": 0.041944155999999566 }, "TrainerController.start_learning": { "total": 411.08515554400014, "count": 1, "self": 0.4441588220030326, "children": { "TrainerController._reset_env": { "total": 8.41085977399996, "count": 1, "self": 8.41085977399996 }, "TrainerController.advance": { "total": 402.14183559099706, "count": 13674, "self": 0.220328301976906, "children": { "env_step": { "total": 401.92150728902016, "count": 13674, "self": 293.6596705350321, "children": { "SubprocessEnvManager._take_step": { "total": 108.03557864499362, "count": 13674, "self": 1.132556729990938, "children": { "TorchPolicy.evaluate": { "total": 106.90302191500268, "count": 13674, "self": 106.90302191500268 } } }, "workers": { "total": 0.22625810899444332, "count": 13674, "self": 0.0, "children": { "worker_root": { "total": 410.07687975399745, "count": 13674, "is_parallel": true, "self": 219.48200217499425, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004859405000047445, "count": 1, "is_parallel": true, "self": 0.0032774270003983474, "children": { "_process_rank_one_or_two_observation": { "total": 0.001581977999649098, "count": 10, "is_parallel": true, "self": 0.001581977999649098 } } }, "UnityEnvironment.step": { "total": 0.04787330099998144, "count": 1, "is_parallel": true, "self": 0.0006197959999099112, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036776199999621895, "count": 1, "is_parallel": true, "self": 0.00036776199999621895 }, "communicator.exchange": { "total": 0.04496383600007903, "count": 1, "is_parallel": true, "self": 0.04496383600007903 }, "steps_from_proto": { "total": 0.0019219069999962812, "count": 1, "is_parallel": true, "self": 0.00036681500000668166, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015550919999895996, "count": 10, "is_parallel": true, "self": 0.0015550919999895996 } } } } } } }, "UnityEnvironment.step": { "total": 190.5948775790032, "count": 13673, "is_parallel": true, "self": 8.299932106006963, "children": { "UnityEnvironment._generate_step_input": { "total": 4.292583823981886, "count": 13673, "is_parallel": true, "self": 4.292583823981886 }, "communicator.exchange": { "total": 150.548119476995, "count": 13673, "is_parallel": true, "self": 150.548119476995 }, "steps_from_proto": { "total": 27.45424217201935, "count": 13673, "is_parallel": true, "self": 5.180633573072782, "children": { "_process_rank_one_or_two_observation": { "total": 22.273608598946566, "count": 136730, "is_parallel": true, "self": 22.273608598946566 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013406700008999906, "count": 1, "self": 0.00013406700008999906, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 399.04742154609244, "count": 379650, "is_parallel": true, "self": 8.158862471073462, "children": { "process_trajectory": { "total": 205.8162621180195, "count": 379650, "is_parallel": true, "self": 205.32883312401964, "children": { "RLTrainer._checkpoint": { "total": 0.4874289939998562, "count": 3, "is_parallel": true, "self": 0.4874289939998562 } } }, "_update_policy": { "total": 185.07229695699948, "count": 68, "is_parallel": true, "self": 48.80558640599497, "children": { "TorchPPOOptimizer.update": { "total": 136.2667105510045, "count": 6933, "is_parallel": true, "self": 136.2667105510045 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08816729000000123, "count": 1, "self": 0.0008229509999182483, "children": { "RLTrainer._checkpoint": { "total": 0.08734433900008298, "count": 1, "self": 0.08734433900008298 } } } } } } }