AI Paper Atlas

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

Refined Regret for Adversarial MDPs with Linear Function Approximation

Yan Dai, Haipeng Luo, Chen-Yu Wei, Julian Zimmert

ICML 2023 · Bandits and online learning › RL theory and MDPs · approach: Regret bounds with function approximation · 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
Replace the previous linear-Q method with refined log-barrier FTRLAdversarial linear-Q MDPs with a simulator · Adversarial linear-Q MDP, simulatorregret: \Otil(d^{2/3} H^2 K^{2/3}) -> \Otil(H^3\sqrt{AdK})Improved
Use a magnitude-reduced Q-function estimator with negative-entropy FTRLAdversarial linear-Q MDPs with a simulator · Adversarial linear-Q MDP, simulatorregret: \Otil(H^3\sqrt{AdK}) -> \Otil(H^3\sqrt{dK})Improved
Replace the prior covariance-inverse estimation procedure with the empirical regularized inverseAdversarial linear MDPs without a simulator · Adversarial linear MDP, no simulatorregret: \Otil(d^2H^4 K^{14/15}) -> \Otil(H^{20/9}A^{1/9}d^{2/3}K^{8/9})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