Grouped Satisficing Paths in Pure Strategy Games: a Topological Perspective
Abstract
In game theory and multi-agent reinforcement learning (MARL), each agent selects a strategy, interacts with the environment and other agents, and subsequently updates its strategy based on the received payoff. This process generates a sequence of joint strategies , where represents the strategy profile of all agents at time step . A widely adopted principle in MARL algorithms is "win-stay, lose-shift", which dictates that an agent retains its current strategy if it achieves the best response. This principle exhibits a fixed-point property when the joint strategy has become an equilibrium. The sequence of joint strategies under this principle is referred to as a satisficing path, a concept first introduced in [40] and explored in the context of -player games in [39]. A fundamental question arises regarding this principle: Under what conditions does every initial joint strategy admit a finite-length satisficing path where and is an equilibrium? This paper establishes a sufficient condition for such a property, and demonstrates that any finite-state Markov game, as well as any -player game, guarantees the existence of a finite-length satisficing path from an arbitrary initial strategy to some equilibrium. These results provide a stronger theoretical foundation for the design of MARL algorithms.
Cite
@article{arxiv.2509.23157,
title = {Grouped Satisficing Paths in Pure Strategy Games: a Topological Perspective},
author = {Yanqing Fu and Chao Huang and Chenrun Wang and Zhuping Wang},
journal= {arXiv preprint arXiv:2509.23157},
year = {2025}
}