AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Regret Bounds for Risk-Sensitive Reinforcement Learning

Osbert Bastani, Yecheng Jason Ma, Estelle Shen, Wanqiao Xu

NeurIPS 2022 · Bandits and online learning › RL theory and MDPs · approach: Regret bounds with function approximation · 1 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 optimistic exploration instead of greedy explorationRisk-sensitive policy learning · Frozen Lake, CVaR α=0.33regret convergenceImproved
use a risk-sensitive objective rather than expected returnFrozen Lake exploration · Frozen Lake, CVaR α=0.33regret convergenceMixed
decrease CVaR tail size α (ablation)Risk-sensitive UCB · Frozen Lake, CVaRregret convergence speedHurt

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