Timezone: »
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.
Author Information
Marek Petrik (University of New Hampshire)
Reaz 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
-
2020 Poster: Bayesian Robust Optimization for Imitation Learning »
Daniel Brown · Scott Niekum · Marek Petrik -
2019 Workshop: Safety and Robustness in Decision-making »
Mohammad Ghavamzadeh · Shie Mannor · Yisong Yue · Marek Petrik · Yinlam Chow -
2018 Poster: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2018 Spotlight: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2016 Poster: Safe Policy Improvement by Minimizing Robust Baseline Regret »
Mohammad Ghavamzadeh · Marek Petrik · Yinlam Chow -
2014 Workshop: From Bad Models to Good Policies (Sequential Decision Making under Uncertainty) »
Odalric-Ambrym Maillard · Timothy A Mann · Shie Mannor · Jeremie Mary · Laurent Orseau · Thomas Dietterich · Ronald Ortner · Peter Grünwald · Joelle Pineau · Raphael Fonteneau · Georgios Theocharous · Esteban D Arcaute · Christos Dimitrakakis · Nan Jiang · Doina Precup · Pierre-Luc Bacon · Marek Petrik · Aviv Tamar -
2014 Poster: RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning »
Marek Petrik · Dharmashankar Subramanian -
2014 Spotlight: RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning »
Marek Petrik · Dharmashankar Subramanian