Transfer in Reinforcement Learning Domains
Transfer in Reinforcement Learning Domains
复制标题
强化学习领域的迁移
DOI：
10.1007/978-3-642-01882-4
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
Matthew E. Taylor
中科院分区：
文献类型：
--
作者：
Matthew E. Taylor
在强化学习（RL）问题中，学习代理以最大化奖励信号为目标顺序执行动作。随着能够掌握越来越复杂问题的算法的发展，强化学习框架越来越受欢迎，但是当强化学习代理在没有先验知识的情况下开始学习困难任务时，学习困难任务通常很慢或不可行的。“迁移学习”背后的关键观点是，泛化不仅可能发生在任务内部，也可能发生在任务之间。虽然迁移在心理学文献中已经研究了很多年，但RL社区直到最近才开始调查知识迁移的好处。这本书提供了RL转移问题的介绍，并讨论了证明这个令人兴奋的研究领域的承诺的方法。本书的主要贡献有：RL领域迁移问题的定义RL领域的背景，足以让广大读者理解所讨论的迁移概念RL中迁移方法的分类现有方法的调查深入介绍所选择的迁移方法讨论关键开放性问题通过本书中提出的研究方式，作者已经确立了自己在序列决策任务迁移学习方面的杰出全球专家地位。研究的一个特别的优势是它非常彻底和有条理的经验评估，马修提出，激励，并在整本书的散文清晰地分析。无论这是你对迁移学习概念的初次介绍，还是你是在寻找细微细节的领域的从业者，我相信你会发现这本书是一本令人愉快和有启发性的读物。Peter Stone，计算机科学副教授
In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently begun to investigate the benefits of transferring knowledge. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research. The key contributions of this book are: Definition of the transfer problem in RL domains Background on RL, sufficient to allow a wide audience to understand discussed transfer concepts Taxonomy for transfer methods in RL Survey of existing approaches In-depth presentation of selected transfer methods Discussion of key open questions By way of the research presented in this book, the author has established himself as the pre-eminent worldwide expert on transfer learning in sequential decision making tasks. A particular strength of the research is its very thorough and methodical empirical evaluation, which Matthew presents, motivates, and analyzes clearly in prose throughout the book. Whether this is your initial introduction to the concept of transfer learning, or whether you are a practitioner in the field looking for nuanced details, I trust that you will find this book to be an enjoyable and enlightening read. Peter Stone, Associate Professor of Computer Science