Searcharxiv⌕ Search

arXiv · 2611.17286

Fictitious Play When Agents Are Not Expected-Utility Maximizers: A Geometric Analysis in $2$-Action Games

Abstract

Fictitious play (FP) is one of the earliest and most fundamental learning procedures in games, where each agent independently chooses a best response to the empirical distribution of opponents' past actions by maximizing the expected payoff with respect to it. However, learning agents may not always be expected-utility maximizers: they may use nonlinear evaluation functionals to account for the uncertainty induced by the opponents, e.g., via risk measures. In this work, we study nonlinear fictitious play (NL-FP), in which each pure action is evaluated by a general, possibly nonlinear functional of the payoff distribution induced by the opponent's empirical belief. To analyze NL-FP, we first identify a single-crossing property (SCP) of evaluation functionals that preserves the classical geometry of FP in $2\times2$ games. Furthermore, we conduct a novel geometric analysis of the convergence behavior of NL-FP in $2\times2$ games, even when the SCP fails. Beyond $2\times2$ games, we show that the convergence of NL-FP in $2\times n$ ($n\ge3$) games may fail even for continuous-time NL-FP, when the two-action player uses conditional value-at-risk (CVaR) in a $2\times3$ game. In addition, we identify a finite-crossing condition that ensures convergence of the selected continuous-time dynamics and the discrete-time iterates in general $2\times n$ games, which also provides new insights into the global landscape of continuous-time classical FP in such games.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hao Liang, Solaleh Mohammadi, Kaiqing Zhang. 2026-11-12. Fictitious Play When Agents Are Not Expected-Utility Maximizers: A Geometric Analysis in $2$-Action Games. https://searcharxiv.com/abs/2611.17286

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

On the closest balanced game

Cooperative games with nonempty core are called balanced, and the set of balanced games is a polyhedron. Given a game with empty core, we look for the closest balanced game, in the sense of the (weighted) Euclidean distance, i.e., the orthogonal projection of the game on the set of balanced games. Besides an analytical approach which becomes rapidly intractable, we propose a fast algorithm to find the closest balanced game, avoiding exponential complexity for the optimization problem, and being able to run up to 20 players. We show experimentally that the probability that the closest game has a core reduced to a singleton tends to 1 when the number of players grow. We provide a mathematical proof that the proportion of facets whose games have a non-singleton core tends to 0 when the number of players grow, by finding an expression of the aymptotic growth of the number of minimal balanced collections. This permits to prove mathematically the experimental result. Consequently, taking the core of the projected game defines a new solution concept, which we call least square core due to its analogy with the least core, and our result shows that the probability that this is a point solution tends to 1 when the number of players grow.

cs.GT↗

Concave is the New Linear: Sybil Attacks Collapse Anti-Plutocratic DAO Voting

Decentralized Autonomous Organizations (DAOs) run protocol governance by letting token holders vote on proposals. The dominant rule, voting power proportional to wallet balance, concentrates control among a small number of large holders, fueling the token-control governance attacks that have already compromised real protocols. To counter this concentration, the community has turned to anti-plutocratic voting mechanisms such as Quadratic Voting (QV), which assign sublinear voting power per token with the goal of dampening the influence of large holders. We prove that no voting rule that derives power solely from wallet balance can succeed on a permissionless blockchain. Through a costed model of on-chain voting that captures realistic blockchain frictions -- including per-wallet splitting and voting costs, fixed setup costs, and minimum-balance requirements -- we show that whenever a wallet of any size yields nonzero voting power, a Sybil attacker who splits tokens across many wallets achieves total voting power that grows at least linearly in their token holdings. For concave rules actually proposed to dampen governance power -- those that are positive, increasing, and finite -- we show that the optimal strategy yields power that is asymptotically linear in token holdings, regardless of the cost scheme. Instantiating the model on real DAOs reveals attack costs orders of magnitude below the value at stake. Replaying the ten most recent finalized proposals of five major DAOs (ENS, Compound, Uniswap, Arbitrum, and ZKsync) under linear, quadratic, logarithmic, and power-($β= 0.25$) voting, we measure Sybil amplification factors between $1,172\times$ and $4,039\times$ under Quadratic Voting, and exceeding $229,000\times$ under steeper power rules.

cs.GT↗

Equilibrium in Multi-Agent Reinforcement Learning

Standard solution concepts for stochastic games, such as MPE and MCCE, are computationally difficult, and thus, standard decentralized reinforcement-learning algorithms should not generally be expected to converge to them. In this paper, we study the equilibrium generated by such algorithms. In particular, we introduce a new solution concept for stochastic games, Markov Bayes coarse correlated equilibrium (MBCCE), defined as a distribution over states and stationary policy profiles such that, after observing the state but before observing her recommended action, no player can gain by choosing a different current action, with the sampled policy profile governing play thereafter. We discuss the parallels between MBCCE and coarse correlated equilibrium (CCE) in finite normal-form games and show that MBCCE retains several of its key properties. We then introduce a corresponding regret notion, adaptive Markov coarse regret (AMCR), and show that vanishing AMCR implies that every accumulation point of the empirical distribution of realized states and policy profiles is an MBCCE. Crucially, we show that achieving AMCR reduces to two standard learning tasks: minimizing external regret at each state and accurately evaluating the current joint policy. We then prove that under mild conditions two natural RL algorithmic designs achieve vanishing AMCR: a decentralized asynchronous actor--critic algorithm through a new two-timescale stochastic-approximation analysis, and a standard episodic multi-agent projected policy-gradient method. Hence, both algorithms approach the MBCCE set, and we establish explicit finite-time convergence rates for both. Finally, we relate MBCCE to stationary MCCE and use this connection together with our algorithmic guarantees to identify a natural class of stochastic games in which these algorithms achieve approximate MCCE.

cs.GT↗