AI Paper Atlas

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

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yian Ma

NeurIPS 2023 · Bandits and online learning › RL theory and MDPs · approach: Linear function approximation in RL · 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 posterior-sampling Delayed-PSVI/Delayed-LPSVI instead of UCB-based Delayed-UCBVI under long-tail Pareto delaysDelayed-feedback RL in linear MDPs · Synthetic linear MDP, Pareto delayaverage return and convergence rateImproved
Use posterior-sampling algorithms instead of Delayed-UCBVI under Multinomial and Poisson delaysDelayed-feedback RL in linear MDPs · Synthetic linear MDP, Multinomial and Poisson delayaverage returnImproved
Heavy-tailed instead of well-behaved delays for Delayed-UCBVIDelayed-UCBVI · Synthetic linear MDPaverage returnHurt
Replace exact posterior sampling with Langevin Monte Carlo (Delayed-LPSVI vs Delayed-PSVI)Delayed-PSVI · Linear MDP regret boundcomputational costImproved
Replace exact posterior sampling with LMCDelayed-PSVI · Linear MDP regret boundworst-case regretNo clear effect

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