paper-with-me

Papers

Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes

2026-06-26 · Luis Leal arxiv

Many two-player zero-sum games admit not a unique Nash equilibrium but a convex set of them: a polytope of profiles that all share the minimax value V* yet prescribe different behaviour. Standard solvers each converge to some equilibrium and are treated as interchangeable. We ask whether they instead select different members of the Nash set, systematically as a function of the algorithm rather than the seed. Using a tabular, exactly solvable testbed of six games with analytically known Nash sets -- including a two-dimensional Nash polytope and Kuhn poker -- we find that (i) selection is determined by the algorithm, not the seed, but families differ only on asymmetric Nash sets; (ii) regularized last-iterate methods (R-NaD, magnetic mirror descent) select the maximum-entropy member, the information projection of their uniform reference onto the Nash set -- exactly on the 2-D polytope and at 99.7% of maximum entropy in Kuhn -- while regret-averaging methods (CFR, CFR+, fictitious play) drift to a lower-entropy face; we confirm this on a randomized 180-game ensemble, where R-NaD attains the maximum-entropy member in 100% of converged games while CFR+ sits strictly below it in 94% (paired Wilcoxon p < 10^-27); (iii) the selected member has downstream consequences against sub-optimal opponents that scale with sequential/hidden-information structure but stay bounded -- in Kuhn the max-entropy member is a strictly better hedge, whereas on the matrix games the members differ without either dominating. We also report two negative results correcting common intuitions: removing CFR's positive-orthant (max(R,0)) projection does not eliminate boundary drift; and R-NaD's selection is anchor-following, not initialization-independent. We state the maximum-entropy / I-projection characterization as a strongly data-supported conjecture, checked throughout against analytic ground truth.

📄 PDF Abstract BibTeX arXiv:2606.28308

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Minimax Sample Complexity for Turn-based Stochastic Game

2020-11-29 · Qiwen Cui, Lin F. Yang

The empirical success of Multi-agent reinforcement learning is encouraging, while few theoretical guarantees have been revealed. In this work, we prove that the plug-in solver approach, probably the most natural reinforc…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Differentiable Arbitrating in Zero-sum Markov Games

2023-02-20 · Jing Wang, Meichen Song, Feng Gao, Boyi Liu 외

We initiate the study of how to perturb the reward in a zero-sum Markov game with two players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a bi-level optimization formulation. The low…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers

2022-10-17 · Luke Marris, Ian Gemp, Thomas Anthony, Andrea Tacchetti 외

Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. Unfortunately, solving a normal-form game could ta…

Zero-shot Generalization

A Generalized Training Approach for Multiagent Learning

2019-09-27 · ICLR 2020 1 · Paul Muller, Shayegan Omidshafiei, Mark Rowland, Karl Tuyls 외

This paper investigates a population-based training regime based on game-theoretic principles called Policy-Spaced Response Oracles (PSRO). PSRO is general in the sense that it (1) encompasses well-known algorithms such …

MuJoCo

A Hybrid Adaptive Nash Equilibrium Solver for Distributed Multi-Agent Systems with Game-Theoretic Jump Triggering

2025-06-12 · Qiuyu Miao, Zhigang Wu

This paper presents a hybrid adaptive Nash equilibrium solver for distributed multi-agent systems incorporating game-theoretic jump triggering mechanisms. The approach addresses fundamental scalability and computational …

Computational Efficiency