Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Dake Zhang, Boxiang Lyu, Shuang Qiu*, Mladen Kolar, Tong Zhang

*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

1 Citation (Scopus)

Abstract

We study risk-sensitive reinforcement learning (RL), a crucial field due to its ability to enhance decision-making in scenarios where it is essential to manage uncertainty and minimize potential adverse outcomes.Particularly, our work focuses on applying the entropic risk measure to RL problems.While existing literature primarily investigates the online setting, there remains a large gap in understanding how to efficiently derive a near-optimal policy based on this risk measure using only a pre-collected dataset.We center on the linear Markov Decision Process (MDP) setting, a well-regarded theoretical framework that has yet to be examined from a risk-sensitive standpoint.In response, we introduce two provably sample-efficient algorithms.We begin by presenting a risk-sensitive pessimistic value iteration algorithm, offering a tight analysis by leveraging the structure of the risk-sensitive performance measure.To further improve the obtained bounds, we propose another pessimistic algorithm that utilizes variance information and reference-advantage decomposition, effectively improving both the dependence on the space dimension d and the risk-sensitivity factor.To the best of our knowledge, we obtain the first provably efficient risk-sensitive offline RL algorithms. Copyright 2024 by the author(s)
Original languageEnglish
Title of host publicationProceedings of the 41st International Conference on Machine Learning
EditorsRuslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, Felix Berkenkamp
PublisherML Research Press
Pages59459-59489
Publication statusPublished - Jul 2024
Externally publishedYes
Event41st International Conference on Machine Learning (ICML 2024) - Messe Wien Exhibition Congress Center, Vienna, Austria
Duration: 21 Jul 202427 Jul 2024
https://proceedings.mlr.press/v235/
https://icml.cc/

Publication series

NameProceedings of Machine Learning Research
Volume235
ISSN (Print)2640-3498

Conference

Conference41st International Conference on Machine Learning (ICML 2024)
Country/TerritoryAustria
CityVienna
Period21/07/2427/07/24
Internet address

Fingerprint

Dive into the research topics of 'Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning'. Together they form a unique fingerprint.

Cite this