{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0869749784469604, "min": 1.0431571006774902, "max": 2.8562872409820557, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10378.4375, "min": 10357.28125, "max": 29251.23828125, "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": 12.56445598602295, "min": 0.501064658164978, "max": 12.56445598602295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2450.06884765625, "min": 97.20654296875, "max": 2522.633544921875, "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": 0.06416949448227088, "min": 0.06020882915198694, "max": 0.07590036873429484, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25667797792908353, "min": 0.24912476044361637, "max": 0.3795018436714742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23705262347471479, "min": 0.137863690784548, "max": 0.2703110798462933, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9482104938988591, "min": 0.551454763138192, "max": 1.344168497066872, "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": 24.863636363636363, "min": 3.9318181818181817, "max": 24.863636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1094.0, "min": 173.0, "max": 1353.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.863636363636363, "min": 3.9318181818181817, "max": 24.863636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1094.0, "min": 173.0, "max": 1353.0, "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": "1716430122", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "1716430615" }, "total": 493.21598554, "count": 1, "self": 0.755558533999988, "children": { "run_training.setup": { "total": 0.05745261300000948, "count": 1, "self": 0.05745261300000948 }, "TrainerController.start_learning": { "total": 492.402974393, "count": 1, "self": 0.6600980939939518, "children": { "TrainerController._reset_env": { "total": 3.4826683339999818, "count": 1, "self": 3.4826683339999818 }, "TrainerController.advance": { "total": 488.11450235200607, "count": 18205, "self": 0.311048032011513, "children": { "env_step": { "total": 487.80345431999456, "count": 18205, "self": 318.5607078009949, "children": { "SubprocessEnvManager._take_step": { "total": 168.91610837500446, "count": 18205, "self": 1.6426664130038944, "children": { "TorchPolicy.evaluate": { "total": 167.27344196200056, "count": 18205, "self": 167.27344196200056 } } }, "workers": { "total": 0.3266381439951829, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 490.95343751300413, "count": 18205, "is_parallel": true, "self": 247.19530554899995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005668344000014258, "count": 1, "is_parallel": true, "self": 0.0038777750002054745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017905689998087837, "count": 10, "is_parallel": true, "self": 0.0017905689998087837 } } }, "UnityEnvironment.step": { "total": 0.08905516699996952, "count": 1, "is_parallel": true, "self": 0.0006894699999975273, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043464899999889894, "count": 1, "is_parallel": true, "self": 0.00043464899999889894 }, "communicator.exchange": { "total": 0.08591477300001316, "count": 1, "is_parallel": true, "self": 0.08591477300001316 }, "steps_from_proto": { "total": 0.0020162749999599328, "count": 1, "is_parallel": true, "self": 0.0003785490001746439, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016377259997852889, "count": 10, "is_parallel": true, "self": 0.0016377259997852889 } } } } } } }, "UnityEnvironment.step": { "total": 243.75813196400418, "count": 18204, "is_parallel": true, "self": 10.972085443013611, "children": { "UnityEnvironment._generate_step_input": { "total": 6.025069310994127, "count": 18204, "is_parallel": true, "self": 6.025069310994127 }, "communicator.exchange": { "total": 189.49509720900244, "count": 18204, "is_parallel": true, "self": 189.49509720900244 }, "steps_from_proto": { "total": 37.265880000994, "count": 18204, "is_parallel": true, "self": 7.201796944951411, "children": { "_process_rank_one_or_two_observation": { "total": 30.06408305604259, "count": 182040, "is_parallel": true, "self": 30.06408305604259 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016941600006248336, "count": 1, "self": 0.00016941600006248336, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.21375901698514, "count": 706780, "is_parallel": true, "self": 15.17316582489309, "children": { "process_trajectory": { "total": 267.9165515370911, "count": 706780, "is_parallel": true, "self": 266.9998665560911, "children": { "RLTrainer._checkpoint": { "total": 0.9166849810000031, "count": 4, "is_parallel": true, "self": 0.9166849810000031 } } }, "_update_policy": { "total": 199.12404165500095, "count": 90, "is_parallel": true, "self": 64.13757205399622, "children": { "TorchPPOOptimizer.update": { "total": 134.98646960100473, "count": 4587, "is_parallel": true, "self": 134.98646960100473 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1455361969999558, "count": 1, "self": 0.001404744999945251, "children": { "RLTrainer._checkpoint": { "total": 0.14413145200001054, "count": 1, "self": 0.14413145200001054 } } } } } } }