Timezone: »

Reinforcement Learning in Robust Markov Decision Processes
Shiau Hong Lim · Huan Xu · Shie Mannor

Sun Dec 08 02:00 PM -- 06:00 PM (PST) @ Harrah's Special Events Center, 2nd Floor

An important challenge in Markov decision processes is to ensure robustness with respect to unexpected or adversarial system behavior while taking advantage of well-behaving parts of the system. We consider a problem setting where some unknown parts of the state space can have arbitrary transitions while other parts are purely stochastic. We devise an algorithm that is adaptive to potentially adversarial behavior and show that it achieves similar regret bounds as the purely stochastic case.

Author Information

Shiau Hong Lim (National University of Singapore)
Huan Xu (National University of Singapore)
Shie Mannor (Technion)

More from the Same Authors