小样本场景下的强化学习研究综述  

Review of Research on Reinforcement Learning in Few-Shot Scenes

作　　者：王哲超 傅启明[1,2,3] 陈建平[2,3] 胡伏原[1,2,3] 陆悠[1,2,3] 吴宏杰 Wang Zhechao;Fu Qiming;Chen Jianping;Hu Fuyuan;Lu You;Wu Hongjie(School of Electronic and Information Engineering,Suzhou University of Science and Technology,Suzhou 215009,China;Jiangsu Provincial Key Laboratory of Building Intelligence and Energy Saving,Suzhou University of Science and Technology,Suzhou 215009,China;Suzhou Key Laboratory of Mobile Networking and Applied Technologies,Suzhou University of Science and Technology,Suzhou 215009,China)

机构地区：[1]苏州科技大学电子与信息工程学院,江苏苏州215009 [2]苏州科技大学江苏省建筑智慧节能重点实验室,江苏苏州215009 [3]苏州科技大学苏州市移动网络技术与应用重点实验室,江苏苏州215009

出　　处：《南京师范大学学报（工程技术版）》2022年第1期86-92,共7页Journal of Nanjing Normal University(Engineering and Technology Edition)

基　　金：国家重点研发计划项目(2020YFC2006602);国家自然科学基金项目(62072324、61876217、61876121、61772357、62073231、61902272);江苏省重点研发计划项目(BE2017663)。

摘　　要：根据小样本问题背景,将小样本场景分成两类,第一类场景追求更专业的性能,第二类场景追求更通用的性能.一般在知识泛化过程中,不同的场景对知识载体的需求有着明显的倾向性.针对小样本学习方法,以知识载体的角度,将其分为使用过程性知识的方法和使用陈述性知识的方法,再讨论该分类下的小样本强化学习算法.最后,从理论和应用等方面提出了可能的发展方向,以期为后续研究提供参考.According to the background of the few-shot problem, this paper divides few-shot scenes into two types. The first type of scenes pursues more professional performance, while the other pursues more general performance. In the process of knowledge generalization, different scenes have obvious tendency to the requirement of knowledge carrier. Because of the discovery, the FSL is divided into two types in terms of knowledge carrier, where one type uses procedural knowledge and the other uses declarative knowledge. Then FS-RL algorithms under this classification are discussed. Finally, the possible development direction is proposed from the theory and the application, hoping to provide insights to following research.

关 键 词：强化学习 小样本学习 元学习 迁移学习 终身学习 知识泛化 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]