Timezone: »

 
Poster
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs
Marek Petrik · Reazul Hasan Russel

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #185
in Reinforcement Learning and Planning -- Model-Based RL »

Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. Existing methods construct ambiguity sets as confidence regions using concentration inequalities which leads to overly conservative solutions. This paper proposes a new paradigm that can achieve better solutions with the same robustness guarantees without using confidence regions as ambiguity sets. To incorporate prior knowledge, our algorithms optimize the size and position of ambiguity sets using Bayesian inference. Our theoretical analysis shows the safety of the proposed method, and the empirical results demonstrate its practical promise.

Keywords: Reinforcement Learning · Model-Based RL · Reinforcement Learning and Planning · Reinforcement Learning and Planning -> Decision and Control; Reinforcement Learning and Planning
[ Paper]  [ Poster] 

Author Information

Marek Petrik (University of New Hampshire)
Reazul Hasan Russel (University of New Hampshire)

I'm a PhD student at the computer science department at University of New Hampshire. I am interested about applying Reinforcement Learning into real world problems with safety and robustness guarantees.

More from the Same Authors