摘要
强化学习是机器学习领域的研究热点,是考察智能体与环境的相互作用,做出序列决策、优化策略并最大化累积回报的过程.强化学习具有巨大的研究价值和应用潜力,是实现通用人工智能的关键步骤.本文综述了强化学习算法与应用的研究进展和发展动态,首先介绍强化学习的基本原理,包括马尔可夫决策过程、价值函数、探索-利用问题.其次,回顾强化学习经典算法,包括基于价值函数的强化学习算法、基于策略搜索的强化学习算法、结合价值函数和策略搜索的强化学习算法,以及综述强化学习前沿研究,主要介绍多智能体强化学习和元强化学习方向.最后综述强化学习在游戏对抗、机器人控制、城市交通和商业等领域的成功应用,以及总结与展望.
Reinforcement learning(RL)is a research hotpot in the machine learning area,which is considering a process of agent-environment interaction,sequential decision making,and total reward maximization.Reinforcement learning is worthy of in-depth research and a wide range of applications in the real world,and represents a vital step toward the Artificial General Intelligence(AGI).In this survey,we review the research progress and development in the algorithms and applications for reinforcement learning.We start with a brief review of the principle of reinforcement learning,including Markov decision process,value function,and exploration v.s.exploitation.Next,we discuss the traditional RL algorithms,including value-based algorithms,policy-based algorithms,and Actor-Critic algorithms,and further discuss the frontiers of RL algorithms,including multi-agent reinforcement learning and meta reinforcement learning.Then,we sketch some successful RL applications in the fields of games,robotics,urban traffic,and business.Finally,we summarize briefly and prospect the development trends of reinforcement learning.
作者
李茹杨
彭慧民
李仁刚
赵坤
LI Ru-Yang;PENG Hui-Min;LI Ren-Gang;ZHAO Kun(Inspur(Beijing)Electronic Information Industry Co.Ltd.,Beijing 100085,China;State Key Laboratory of High-End Server&Storage Technology,Inspur Group Co.Ltd.,Beijing 100085,China;Guangdong Inspur Big Data Research Co.Ltd.,Guangzhou 510632,China)
出处
《计算机系统应用》
2020年第12期13-25,共13页
Computer Systems & Applications
关键词
强化学习
算法
应用
多智能体强化学习
元强化学习
reinforcement learning
algorithms
applications
multi-agent reinforcement learning
meta reinforcement learning