计算机工程与应用2018，Vol.54Issue(5)：24-35,12.DOI:10.3778/j.issn.1002-8331.1711-0289
深度逆向强化学习研究综述
Overview of deep inverse reinforcement learning
摘要
Abstract
Deep inverse reinforcement learning is a new research hotspot in the field of machine learning.It aims at recovering the reward function of deep reinforcement learning by the experts'example trajectories.This paper systematically introduces three kinds of classic deep reinforcement learning methods.Then inverse reinforcement learning algorithms including apprenticeship learning,max margin plan,structured classification and probability models are described;then, some frontier researches of deep inverse reinforcement learning are reviewed,including the deep max margin plan inverse reinforcement learning,deep inverse reinforcement learning based on DQN and deep maximum entropy inverse reinforce-ment learning and recovering reward functions from non-expert trajectories etc.Finally,the existing issues and develop-ment direction are summarized.关键词
深度学习/强化学习/深度逆向强化学习Key words
deep learning/reinforcement learning/deep inverse reinforcement learning分类
信息技术与安全科学引用本文复制引用
陈希亮,曹雷,何明,李晨溪,徐志雄..深度逆向强化学习研究综述[J].计算机工程与应用,2018,54(5):24-35,12.基金项目
国家重点研发计划(No.2016YFC0800606) （No.2016YFC0800606）
中国工程院重点咨询课题(No.2017-XZ-05) （No.2017-XZ-05）
总装备部预研基金(No. 9140A06020315JB25081) （No. 9140A06020315JB25081）
江苏省自然科学基金(No.BK20161469,No.BK20150721) （No.BK20161469,No.BK20150721）
中国博士后基金(No.2015M582786, No.2016T91017) （No.2015M582786, No.2016T91017）
江苏省重点研发计划(No.BE2015728,No.BE2016904). （No.BE2015728,No.BE2016904）
