AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

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

Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Matthieu Geist, Yuejie Chi

NeurIPS 2023 · Reinforcement learning › MDPs and planning · approach: Offline RL sample complexity · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use total variation uncertainty set (robust MDP) instead of standard MDPDRVI · TV-distance RMDPsample complexityImproved
tight analysis of DRVI for TV distance over full range of uncertainty levelDRVI · DRVIsample complexity upper boundImproved
use chi-square divergence uncertainty set instead of standard MDPDRVI · chi-square RMDPsample complexityMixed
new analysis of DRVI for chi-square setDRVI · chi-square RMDPdependence on state space size SImproved
increase uncertainty level sigma toward 1 under TV distanceDRVI · TV-distance RMDPsample complexityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy