The reviewed record of science sign in
Pith

arxiv: 2201.03522 · v2 · pith:NIBGPROU · submitted 2022-01-10 · cs.LG · cs.AI· cs.GT· stat.ML

When is Offline Two-Player Zero-Sum Markov Game Solvable?

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:NIBGPROUrecord.jsonopen to challenge →

classification cs.LG cs.AIcs.GTstat.ML
keywords assumptionmarkovofflineconcentrationgameslearningstrategytwo-player
0
0 comments X
read the original abstract

We study what dataset assumption permits solving offline two-player zero-sum Markov games. In stark contrast to the offline single-agent Markov decision process, we show that the single strategy concentration assumption is insufficient for learning the Nash equilibrium (NE) strategy in offline two-player zero-sum Markov games. On the other hand, we propose a new assumption named unilateral concentration and design a pessimism-type algorithm that is provably efficient under this assumption. In addition, we show that the unilateral concentration assumption is necessary for learning an NE strategy. Furthermore, our algorithm can achieve minimax sample complexity without any modification for two widely studied settings: dataset with uniform concentration assumption and turn-based Markov games. Our work serves as an important initial step towards understanding offline multi-agent reinforcement learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Sample-efficient inductive matrix completion with noise and inexact side-information

    stat.ML 2026-05 unverdicted novelty 7.0

    Nonconvex projected gradient descent for noisy inductive matrix completion achieves linear convergence and order-optimal error at sample complexity scaling with side-information dimension a instead of ambient dimension n.

  2. Sample-efficient inductive matrix completion with noise and inexact side-information

    stat.ML 2026-05 unverdicted novelty 7.0

    A projected gradient descent algorithm for noisy inductive matrix completion achieves linear convergence and stable recovery at sample complexity governed by side-information dimension, extending to inexact side-infor...