| 强化学习及其在电脑围棋中的应用 |
| |
| 引用本文： | 陈兴国,俞扬.强化学习及其在电脑围棋中的应用[J].自动化学报,2016,42(5):685-695. |
| |
| 作者姓名： | 陈兴国 俞扬 |
| |
| 作者单位： | 1.南京邮电大学计算机学院/软件学院 南京 210046 |
| |
| 基金项目： | 国家自然科学基金(61403208,61375061),南京邮电大学引进人才科研启动基金(NY214014)资助 |
| |
| 摘 要： | 强化学习是一类特殊的机器学习, 通过与所在环境的自主交互来学习决策策略, 使得策略收到的长期累积奖赏最大. 最近, 在围棋和电子游戏等领域, 强化学习被成功用于取得人类水平的操作能力, 受到了广泛关注. 本文将对强化学习进行简要介绍, 重点介绍基于函数近似的强化学习方法, 以及在围棋等领域中的应用.
|
| 关 键 词： | 强化学习 函数近似 核方法 神经网络 加性模型 深度强化学习 |
| 收稿时间： | 2016-04-28 |
Reinforcement Learning and Its Application to the Game of Go |
| |
| CHEN Xing-Guo,YU Yang.Reinforcement Learning and Its Application to the Game of Go[J].Acta Automatica Sinica,2016,42(5):685-695. |
| |
| Authors: | CHEN Xing-Guo YU Yang |
| |
| Affiliation: | 1.Nanjing University of Posts and Telecommunications, School of Computer Science & Technology, School of Software, Nanjing 2100462.National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023 |
| |
| Abstract: | Reinforcement learning is a particular type of machine learning that autonomously learns from interactions with the environment, so that its long-term reward is maximized. It has recently been successfully applied to playing the game of Go and video games, and human expert level is demonstrated. Since these results are receiving increasing attentions, this paper briefly introduces reinforcement learning, focusing on the methods with function approximation, and its applications in the game of Go. |
| |
| Keywords: | Reinforcement learning linear function approximation kernel methods neural networks additive model deep reinforcement learning |
|
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
