Accuracy-Time Efficient Hyperparameter Optimization Using Actor-Critic-based Reinforcement Learning and Early Stopping in OpenAI Gym Environment

Albert Budi Christian, Chih Yu Lin, Yu Chee Tseng, Lan Da Van, Wan Hsun Hu, Chia Hsuan Yu

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

In this paper, we present accuracy-time efficient hyperparameter optimization (HPO) using advantage actor-critic (A2C)-based reinforcement learning (RL) and early stopping in OpenAI Gym environment. The A2C RL can improve the hyperparameter selection such that the resulting accuracy of machine learning (ML) algorithms including XGBoost, support vector classifier (SVC), random forest shows comparable. According to the specified accuracy of the ML algorithms, the early stopping scheme can save the computation cost. Ten standard datasets are used to valid the accuracy-time efficient HPO. Experimental results show that the presented accuracy-efficient HPO architecture can improve 0.77% accuracy on average compared with default hyperparameter for random forest. The early stopping can save 64% computation cost on average compared to without early stopping for random forest.

原文English
主出版物標題Proceedings of the 2022 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面230-234
頁數5
ISBN(電子)9798350396454
DOIs
出版狀態Published - 2022
事件2022 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2022 - Virtual, Online, 印度尼西亞
持續時間: 24 11月 202226 11月 2022

出版系列

名字Proceedings of the 2022 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2022

Conference

Conference2022 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2022
國家/地區印度尼西亞
城市Virtual, Online
期間24/11/2226/11/22

指紋

深入研究「Accuracy-Time Efficient Hyperparameter Optimization Using Actor-Critic-based Reinforcement Learning and Early Stopping in OpenAI Gym Environment」主題。共同形成了獨特的指紋。

引用此