{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.700901448726654, "min": 0.700901448726654, "max": 2.8635528087615967, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7185.6416015625, "min": 7061.4638671875, "max": 29325.64453125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.612013816833496, "min": 0.5126138925552368, "max": 13.619711875915527, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2776.850830078125, "min": 99.44709014892578, "max": 2789.6025390625, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07091134904692058, "min": 0.06205288498181556, "max": 0.0752996457826264, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3545567452346029, "min": 0.24821153992726225, "max": 0.3703757430874557, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1721243348191766, "min": 0.11575145565644454, "max": 0.28979249642175786, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.860621674095883, "min": 0.46300582262577816, "max": 1.4489624821087892, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333332e-06, "min": 5.288098237333332e-06, "max": 0.0002945880018039999, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.644049118666666e-05, "min": 2.644049118666666e-05, "max": 0.00142344002552, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666664, "min": 0.10176266666666664, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333332, "min": 0.42025066666666666, "max": 0.9744800000000001, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999995, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.636363636363637, "min": 3.3863636363636362, "max": 26.84090909090909, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1465.0, "min": 149.0, "max": 1476.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.636363636363637, "min": 3.3863636363636362, "max": 26.84090909090909, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1465.0, "min": 149.0, "max": 1476.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680898932", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680899718" }, "total": 785.6643993170001, "count": 1, "self": 0.3884972190001008, "children": { "run_training.setup": { "total": 0.11393902200006778, "count": 1, "self": 0.11393902200006778 }, "TrainerController.start_learning": { "total": 785.1619630759999, "count": 1, "self": 0.8536561410137438, "children": { "TrainerController._reset_env": { "total": 4.7224962310000365, "count": 1, "self": 4.7224962310000365 }, "TrainerController.advance": { "total": 779.4601881689861, "count": 27333, "self": 0.39885339799945996, "children": { "env_step": { "total": 779.0613347709866, "count": 27333, "self": 592.8370117780241, "children": { "SubprocessEnvManager._take_step": { "total": 185.81948849797425, "count": 27333, "self": 2.702622632958196, "children": { "TorchPolicy.evaluate": { "total": 183.11686586501605, "count": 27333, "self": 183.11686586501605 } } }, "workers": { "total": 0.4048344949882221, "count": 27333, "self": 0.0, "children": { "worker_root": { "total": 782.7533764590105, "count": 27333, "is_parallel": true, "self": 410.91229369800647, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005043701999966288, "count": 1, "is_parallel": true, "self": 0.0034943299999667943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015493719999994937, "count": 10, "is_parallel": true, "self": 0.0015493719999994937 } } }, "UnityEnvironment.step": { "total": 0.0955530109999927, "count": 1, "is_parallel": true, "self": 0.0006120519999512908, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039614299998902425, "count": 1, "is_parallel": true, "self": 0.00039614299998902425 }, "communicator.exchange": { "total": 0.09229571800005942, "count": 1, "is_parallel": true, "self": 0.09229571800005942 }, "steps_from_proto": { "total": 0.002249097999992955, "count": 1, "is_parallel": true, "self": 0.0006179900000233829, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016311079999695721, "count": 10, "is_parallel": true, "self": 0.0016311079999695721 } } } } } } }, "UnityEnvironment.step": { "total": 371.84108276100403, "count": 27332, "is_parallel": true, "self": 15.189042390021541, "children": { "UnityEnvironment._generate_step_input": { "total": 8.586455692006894, "count": 27332, "is_parallel": true, "self": 8.586455692006894 }, "communicator.exchange": { "total": 297.78203568399397, "count": 27332, "is_parallel": true, "self": 297.78203568399397 }, "steps_from_proto": { "total": 50.28354899498163, "count": 27332, "is_parallel": true, "self": 10.075951211017696, "children": { "_process_rank_one_or_two_observation": { "total": 40.207597783963934, "count": 273320, "is_parallel": true, "self": 40.207597783963934 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00043313400010447367, "count": 1, "self": 0.00043313400010447367, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 774.129284379833, "count": 613644, "is_parallel": true, "self": 15.54287752083826, "children": { "process_trajectory": { "total": 379.4028833389932, "count": 613644, "is_parallel": true, "self": 377.4552902719927, "children": { "RLTrainer._checkpoint": { "total": 1.9475930670005255, "count": 6, "is_parallel": true, "self": 1.9475930670005255 } } }, "_update_policy": { "total": 379.1835235200016, "count": 136, "is_parallel": true, "self": 153.28521456799683, "children": { "TorchPPOOptimizer.update": { "total": 225.89830895200475, "count": 11555, "is_parallel": true, "self": 225.89830895200475 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12518940099994325, "count": 1, "self": 0.000866094000002704, "children": { "RLTrainer._checkpoint": { "total": 0.12432330699994054, "count": 1, "self": 0.12432330699994054 } } } } } } }