cs.GTNov 15, 2026

Who Observes Whom: Network Rationalizability and Its Complexity

Authors: Mojtaba Fayaz-Bakhsh, MohammadAmin Fazli

Abstract

Nash equilibrium and rationalizability sit at opposite informational extremes: the former presumes that each player knows all opponents' strategies, the latter that players reason from common knowledge of rationality alone. When visibility is partial and asymmetric, we study the solution concepts induced by a directed observation network GG in which an edge i→ji\to j means that ii observes jj's strategy. A set of profiles is self-sustaining if every profile in it can be justified, for every player, by conjectures from the same set that agree with everything the player observes. We consider point conjectures (single profiles) and belief conjectures (distributions over profiles). Both range from Nash equilibrium on the complete network to point- and correlated rationalizability on the empty network, and shrink monotonically as links are added. Network topology governs both behavior and complexity. A predicted profile can be found in polynomial time on the empty network, whereas a single link makes search PPAD\mathsf{PPAD}-hard: under one-sided two-player monitoring, the observed player's strategies are exactly her Nash equilibrium strategies. On hierarchical networks (transitive tournaments), membership reduces recursively to smaller games and admits polynomial-size certificates, placing verification in ∃R\exists\mathbb{R}, and in P\mathsf{P} for two players. On the directed three-cycle, however, iterated elimination may never terminate under either variant, and under point conjectures interior predictions may admit only infinite witness sets, a pathology that belief conjectures avoid in the same game. Finally, when only realized pure actions are observed, the solution set is guaranteed to be non-empty exactly when the network has no edges, and is computable in time O(n∣A∣2)O(n|A|^2).

Figures & tables

Explore similar work

Oct 29, 2022

Observable Perfect Equilibrium

While Nash equilibrium has emerged as the central game-theoretic solution concept, many important games contain several Nash equilibria and we must determine how to select between them in order to create real strategic agents. Several Nash equilibrium refinement concepts have been proposed and studied for sequential imperfect-information games, the most prominent being trembling-hand perfect equilibrium, quasi-perfect equilibrium, proper equilibrium, and recently one-sided quasi-perfect equilibrium. These concepts are robust to certain arbitrarily small mistakes, and are guaranteed to always exist; however, we argue that none of these is the correct concept for developing strong agents in sequential games of imperfect information. We define a new equilibrium refinement concept for extensive-form games called observable perfect equilibrium in which the solution is robust over trembles in publicly-observable action probabilities (not necessarily over all action probabilities that may not be observable by opposing players). Observable perfect equilibrium correctly captures the assumption that the opponent is playing as rationally as possible given mistakes that have been observed (while previous solution concepts do not). We prove that observable perfect equilibrium is always guaranteed to exist, and demonstrate that it selects a unique equilibrium in a simplified no-limit poker game where the prior extensive-form refinements retain a continuum of equilibria. We expect observable perfect equilibrium to be a useful equilibrium refinement concept for modeling many important imperfect-information games of interest in artificial intelligence.
Apr 9, 2026

Learning to Coordinate over Networks with Bounded Rationality

Network coordination games are widely used to model collaboration among interconnected agents, with applications across diverse domains including economics, robotics, and cyber-security. We consider networks of bounded-rational agents who interact through binary stag hunt games, a canonical game theoretic model for distributed collaborative tasks. Herein, the agents update their actions using logit response functions, yielding the Log-Linear Learning (LLL) algorithm. While convergence of LLL to a risk-dominant Nash equilibrium requires unbounded rationality, we consider regimes in which rationality is strictly bounded. We first show that the stationary probability of states corresponding to perfect coordination is monotone increasing in the rationality parameter ββ. For KK-regular networks, we prove that the stationary probability of a perfectly coordinated action profile is monotone in the connectivity degree KK, and we provide an upper bound on the minimum rationality required to achieve a desired level of coordination. For irregular networks, we show that the stationary probability of perfectly coordinated action profiles increases with the number of edges in the graph. We show that, for a large class of networks, the partition function of the Gibbs measure is well approximated by the moment generating function of Gaussian random variable. This approximation allows us to optimize degree distributions and establishes that the optimal network - i.e., the one that maximizes the stationary probability of coordinated action profiles - is KK-regular. Consequently, our results indicate that networks of uniformly bounded-rational agents achieve the most reliable coordination when connectivity is evenly distributed among agents.
Jan 12, 2022

Safe Equilibrium

The standard game-theoretic solution concept, Nash equilibrium, assumes that all players behave rationally. If we follow a Nash equilibrium and opponents are irrational (or follow strategies from a different Nash equilibrium), then we may obtain an extremely low payoff. On the other hand, a maximin strategy assumes that all opposing agents are playing to minimize our payoff (even if it is not in their best interest), and ensures the maximal possible worst-case payoff, but results in exceedingly conservative play. We propose a new solution concept called safe equilibrium that models opponents as behaving rationally with a specified probability and behaving potentially arbitrarily with the remaining probability. We prove that a safe equilibrium exists in all strategic-form games (for all possible values of the rationality parameters), and prove that its computation is PPAD-hard. We present exact algorithms for computing a safe equilibrium in both 2 and nn-player games, as well as scalable approximation algorithms.