The framework of mean-field games (MFGs) is used for modeling the collective dynamics of large populations of non-cooperative decision-making agents. We formulate and analyze a kinetic MFG model for an interacting system of non-cooperative motile agents with inertial dynamics and finite-range interactions, where each agent is minimizing a biologically inspired cost function. By analyzing the associated coupled forward–backward in a time system of nonlinear Fokker–Planck and Hamilton–Jacobi–Bellman equations, we obtain conditions for closed-loop linear stability of the spatially homogeneous MFG equilibrium that corresponds to an ordered state with non-zero mean speed. Using a combination of analysis and numerical simulations, we show that when energetic cost of control is reduced below a critical value, this equilibrium loses stability, and the system transitions to a traveling wave solution. Our work provides a game-theoretic perspective to the problem of collective motion in non-equilibrium biological and bio-inspired systems.
more »
« less
On Time‐Inconsistency in Mean‐Field Games
ABSTRACT We investigate an infinite‐horizon time‐inconsistent mean‐field game (MFG) in a discrete time setting. We first present a classic equilibrium for the MFG and its associated existence result. This classic equilibrium aligns with the conventional equilibrium concept studied in MFG literature when the context is time‐consistent. Then we demonstrate that while this equilibrium produces an approximate optimal strategy when applied to the related ‐agent games, it does so solely in a precommitment sense. Therefore, it cannot function as a genuinely approximate equilibrium strategy from the perspective of a sophisticated agent within the ‐agent game. To address this limitation, we propose a newconsistentequilibrium concept in both the MFG and the ‐agent game. We show that a consistent equilibrium in the MFG can indeed function as an approximate consistent equilibrium in the ‐agent game. Additionally, we analyze the convergence of consistent equilibria for ‐agent games toward a consistent MFG equilibrium as tends to infinity.
more »
« less
- Award ID(s):
- 2106556
- PAR ID:
- 10627249
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Mathematical Finance
- Volume:
- 35
- Issue:
- 3
- ISSN:
- 0960-1627
- Page Range / eLocation ID:
- 613 to 635
- Subject(s) / Keyword(s):
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In multi-agent dynamic games, the Nash equilibrium state trajectory of each agent is determined by its cost function and the information pattern of the game. However, the cost and trajectory of each agent may be unavailable to the other agents. Prior work on using partial observations to infer the costs in dynamic games assumes an open-loop information pattern. In this work, we demonstrate that the feedback Nash equilibrium concept is more expressive and encodes more complex behavior. It is desirable to develop specific tools for inferring players’ objectives in feedback games. Therefore, we consider the dynamic game cost inference problem under the feedback information pattern, using only partial state observations and incomplete trajectory data. To this end, we first propose an inverse feedback game loss function, whose minimizer yields a feedback Nash equilibrium state trajectory closest to the observa- tion data. We characterize the landscape and differentiability of the loss function. Given the difficulty of obtaining the exact gradient, our main contribution is an efficient gradient approximator, which enables a novel inverse feedback game solver that minimizes the loss using first-order optimization. In thorough empirical evaluations, we demonstrate that our algorithm converges reliably and has better robustness and generalization performance than the open-loop baseline method when the observation data reflects a group of players acting in a feedback Nash game.more » « less
-
We study the problem of computing an approximate Nash equilibrium of a game whose strategy space is continuous without access to gradients of the utility function.Lack of access to gradients is common in reinforcement learning settings, where the environment is treated as a black box, as well as equilibrium finding in mechanisms such as auctions, where the mechanism's payoffs are discontinuous in the players' actions.To tackle this problem, we turn to zeroth-order optimization techniques that combine pseudo-gradients with equilibrium-finding dynamics.Specifically, we introduce a new technique that requires a number of utility function evaluations per iteration that is constant rather than linear in the number of players.It achieves this by performing a single joint perturbation on all players' strategies, rather than perturbing each one individually.This is very important for many-player games, especially when the utility function is expensive to compute in terms of wall time, memory, money, or other resources.We evaluate our approach on various games, including auctions, which have important real-world applications.Our approach yields a dramatic improvement in performance in terms of the wall time required to reach an approximate Nash equilibrium.more » « less
-
A graphon game can be seen either as a limit of a sequence of network games when the number of players tends to infinity or as a stochastic model for sampling network games. Under suitable assumptions, we show that every convergent sequence of Nash equilibria of network games sampled from a graphon game converges to an equilibrium of the graphon game with probability 1, and every equilibrium of a graphon game is a limit of a sequence of approximate Nash equilibria of network games sampled from the graphon game with probability 1. Further, we provide methods for computing the equilibria of two broad classes of graphon games modeling commonly observed interaction structures: graphon games with (i) a low-rank graphon and a polynomial best-response function and (ii) a stochastic block model graphon and finite strategy sets.more » « less
-
There has been substantial progress on finding game-theoretic equilibria. Most of that work has focused on games with finite, discrete action spaces. However, many games involving space, time, money, and other fine-grained quantities have continuous action spaces (or are best modeled as having such). We study the problem of finding an approximate Nash equilibrium of games with continuous action sets. The standard measure of closeness to Nash equilibrium is exploitability, which measures how much players can benefit from unilaterally changing their strategy. We propose two new methods that minimize an approximation of exploitability with respect to the strategy profile. The first method uses a learned best-response function, which takes the current strategy profile as input and outputs candidate best responses for each player. The strategy profile and best-response functions are trained simultaneously, with the former trying to minimize exploitability while the latter tries to maximize it. The second method maintains an ensemble of candidate best responses for each player. In each iteration, the best-performing elements of each ensemble are used to update the current strategy profile. The strategy profile and ensembles are simultaneously trained to minimize and maximize the approximate exploitability, respectively. We evaluate our methods on various continuous games and GAN training, showing that they outperform prior methods.more » « less
An official website of the United States government

