arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.05000cs.LGcs.AI
收藏

自动化强化学习:综述

Automated Reinforcement Learning: An Overview

Eindhoven University of Technology(埃因霍温理工大学);Jheronimus Academy of Data Science(赫尔蒙尼乌斯数据科学学院);Shandong University(山东大学)

Reza Refaei Afshar, Joaquin Vanschoren, Uzay Kaymak, Rui Zhang, Yaoxin Wu, Wen Song, Yingqian Zhang

AI总结:

本文综述了自动化强化学习的发展,包括基于大语言模型的技术,并探讨了其挑战和未来研究方向。

摘要:

强化学习,以及最近的深度强化学习,是解决建模为马尔可夫决策过程的序列决策问题的流行方法。对问题进行强化学习建模并选择算法和超参数需要仔细考虑,因为不同的配置可能导致完全不同的性能。这些考虑主要由强化学习专家负责;然而,强化学习正在逐渐在其他领域流行,如组合优化,其中研究人员和系统设计师不一定是强化学习专家。此外,许多建模决策通常是手动完成的,例如定义状态和动作空间、批次大小、批次更新频率和时间步长。因此,自动化强化学习的不同组件非常重要,近年来吸引了大量关注。自动化强化学习提供了一个框架,其中强化学习的不同组件,包括MDP建模、算法选择和超参数优化,都被建模和定义为自动的。在本文中,我们介绍了自动化强化学习(AutoRL)的相关文献,包括最近基于大语言模型(LLM)的技术。我们还讨论了近期在不专门针对自动化强化学习但有潜力未来整合到AutoRL中的技术。此外,我们还讨论了AutoRL中的挑战、开放问题和研究方向。

英文摘要:

Reinforcement Learning and, recently, Deep Reinforcement Learning are popular methods for solving sequential decision-making problems modeled as Markov Decision Processes. RL modeling of a problem and selecting algorithms and hyper-parameters require careful consideration, as different configurations may entail completely different performances. These considerations are mainly the task of RL experts; however, RL is progressively becoming popular in other fields, such as combinatorial optimization, where researchers and system designers are not necessarily RL experts. Besides, many modeling decisions are typically made manually, such as defining state and action space, size of batches, batch update frequency, and time steps. For these reasons, automating different components of RL is of great importance, and it has attracted much attention in recent years. Automated RL provides a framework in which different components of RL, including MDP modeling, algorithm selection, and hyper-parameter optimization, are modeled and defined automatically. In this article, we present the literature on automated RL (AutoRL), including the recent large language model (LLM) based techniques. We also discuss the recent work on techniques that are not presently tailored for automated RL but hold promise for future integration into AutoRL. Furthermore, we discuss the challenges, open questions, and research directions in AutoRL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑