AI Paper Atlas

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

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang, Qiaomin Xie

NeurIPS 2020 · Bandits and online learning › RL theory and MDPs · approach: Regret bounds with function approximation · 24 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
Increase risk sensitivity |β| and horizon H while requiring sublinear-in-T regretAny algorithm · Episodic MDPexpected regret: \frac{e^{\left|\beta\right|H/2}-1}{\left|\beta\right|}\sqrt{T\log T}Hurt
Take the risk-neutral limit β→0RSVI · Episodic MDPregret upper bound: \sqrt{H^{3}S^{2}AT\log^{2}(2SAT/\delta)}Improved
Take the risk-neutral limit β→0RSQ · Episodic MDPregret upper bound: \sqrt{H^{4}SAT\log(SAT/\delta)}Improved

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