Math 2.0

Resources / preprint

Achieving an $O(1/N)$ Optimality Gap in Average-Reward Weakly-Coupled MDPs K6CP8GP51H

URIm2://res/K6CP8GP51H
Kindpreprint
CreatorsYige Hong, Xiangcheng Zhang, Qiaomin Xie, Yudong Chen, Weina Wang
Date2026-09-29
Subjectsarxiv cs.LG, arxiv math.OC, arxiv math.PR
Scopeborder

Expressions

e1: version, preprint

Date2026-09-29
IdsarXiv 2609.38132

Items in this resource

The mentions of the inventory that name this resource. Each name links to the card of its inventory row.

ItemKindWhereSource
$\errtol$-maximal feasible setdefinitiondefinition 2arxiv
1ST5HR6BFVdefinitiondefinition 1arxiv
3MBNRYX9G7statementlemma 6arxiv
Drift of $\locapprox$statementlemma 5arxiv
5WJMCPNAX3statementproposition 2arxiv
99BSWH9FFDstatementlemma 7arxiv
Rounding error of \lpfpstatementlemma 11arxiv
Inequality feasibility of the affine targetstatementlemma 9arxiv
Sufficient coveragestatementlemma 15arxiv
Properties of $\Vds$statementlemma 2arxiv
Drift of truncated $\Vds$statementlemma 4arxiv
\frcontrol transition dynamicsstatementlemma 10arxiv
Pseudo-contraction under the weighted $L_2$ normsstatementlemma 8arxiv
Dimension of $\Cmat$statementproposition 1arxiv
Almost non-shrinkingstatementlemma 14arxiv
Instantaneous reward under \lpfpstatementlemma 3arxiv
Optimality gap for the WCMDP two-set policystatementtheorem 1arxiv
Properties of $\hw$ and $\hu$statementlemma 13arxiv
\lpfp transition dynamicsstatementlemma 1arxiv
Subroutine conformitystatementlemma 12arxiv

Catalogue records