paper-with-me

Papers

Robust Phi-Divergence MDPs

2022-05-27 · Chin Pang Ho, Marek Petrik, Wolfram Wiesemann

In recent years, robust Markov decision processes (MDPs) have emerged as a prominent modeling framework for dynamic decision problems affected by uncertainty. In contrast to classical MDPs, which only account for stochasticity by modeling the dynamics through a stochastic process with a known transition kernel, robust MDPs additionally account for ambiguity by optimizing in view of the most adverse transition kernel from a prescribed ambiguity set. In this paper, we develop a novel solution framework for robust MDPs with s-rectangular ambiguity sets that decomposes the problem into a sequence of robust Bellman updates and simplex projections. Exploiting the rich structure present in the simplex projections corresponding to phi-divergence ambiguity sets, we show that the associated s-rectangular robust MDPs can be solved substantially faster than with state-of-the-art commercial solvers as well as a recent first-order solution scheme, thus rendering them attractive alternatives to classical MDPs in practical applications.

📄 PDF Abstract BibTeX arXiv:2205.14202

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Variational Planning for Graph-based MDPs

2013-12-01 · NeurIPS 2013 12 · Qiang Cheng, Qiang Liu, Feng Chen, Alexander T. Ihler

Markov Decision Processes (MDPs) are extremely useful for modeling and solving sequential decision making problems. Graph-based MDPs provide a compact representation for MDPs with large numbers of random variables. Howev…

Decision MakingSequential Decision Making

Model-Free Robust Average-Reward Reinforcement Learning

2023-05-17 · Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette 외

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs. In this paper, we focus on the robust average-reward MDPs under…

modelQ-Learningreinforcement-learningReinforcement Learning

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

2023-05-26 · NeurIPS 2023 11 · Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen 외

This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a …

Reinforcement Learning (RL)

Linear Mixture Distributionally Robust Markov Decision Processes

2025-05-23 · Zhishuai Liu, Pan Xu

Many real-world decision-making problems face the off-dynamics challenge: the agent learns a policy in a source domain and deploys it in a target domain with different state transitions. The distributionally robust Marko…

Efficient Algorithms for Robust Markov Decision Processes with $s$-Rectangular Ambiguity Sets

2026-02-05 · Chin Pang Ho, Marek Petrik, Wolfram Wiesemann arxiv

Robust Markov decision processes (MDPs) have attracted significant interest due to their ability to protect MDPs from poor out-of-sample performance in the presence of ambiguity. In contrast to classical MDPs, which acco…