Scaling solutions to Markov Decision Problems

Reinforcement learning;Machine learning;Planning;Artificial intelligence;Markov decision processes

Zang, Peng ; Computing

University:Georgia Institute of Technology

Department:Computing

关键词: Reinforcement learning;    Machine learning;    Planning;    Artificial intelligence;    Markov decision processes;   

Others  :  https://smartech.gatech.edu/bitstream/1853/42906/1/zang_peng_201112_phd.pdf

美国|英语

来源: SMARTech Repository

【 摘 要 】

The Markov Decision Problem (MDP) is a widely applied mathematical model useful for describing a wide array of real world decision problems ranging from navigation to scheduling to robotics. Existing methods for solving MDPs scale poorly when applied to large domains where there are many components and factors to consider.In this dissertation, I study the use of non-tabular representations and human input as scaling techniques. I will show that the joint approach has desirable optimality and convergence guarantees, and demonstrates several orders of magnitude speedup over conventional tabular methods. Empirical studies of speedup were performed using several domains including a clone of the classic video game, Super Mario Bros. In the course of this work, I will address several issues including: how approximate representations can be used without losing convergence and optimality properties, how human input can be solicited to maximize speedup and user engagement, and how that input should be used so as to insulate against possible errors.