AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, Liwei Wang, Simon Shaolei Du

NeurIPS 2023 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 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 multi-batched Phase Elimination with the delayed-feedback reductionLinear bandit · Linear banditregret upper bound: \Tilde{O}(d\sqrt{K}+ d^{3/2}\mathbb{E}[\tau]) -> \Tilde{O}(d\sqrt{K}+\mathbb{E}[\tau])Improved
Use multi-batched policy elimination with the delayed-feedback reductionTabular MDP · Tabular MDPregret upper bound: \Tilde{O}(\sqrt{H^3 S A K }+H^2 S A \mathbb{E}[\tau]\log K ) -> \Tilde{O}\left(\sqrt{S A H^3 K }+ H (H+\log \log K)\mathImproved
Use multi-batched linear MDP and general-function-approximation algorithms with the reductionRL with function approximation · Linear MDP and general function approximationregret upper boundImproved
Use the delayed-feedback reduction with multi-batched algorithmsMarkov games · Tabular and linear Markov gamesregret upper boundImproved

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