English
Related papers

Related papers: Convergence of Payoff-Based Higher-Order Replicato…

200 papers

We investigate the interplay between passivity, no-regret, and convergence in contractive games for various learning dynamic models and their higher-order variants. Our setting is continuous time. Building on prior work for replicator…

Systems and Control · Electrical Eng. & Systems 2025-04-01 Hassan Abdelraouf , Georgios Piliouras , Jeff S. Shamma

In this paper, we propose a passivity-based methodology for analysis and design of reinforcement learning in multi-agent finite games. Starting from a known exponentially-discounted reinforcement learning scheme, we show that convergence to…

Optimization and Control · Mathematics 2024-10-30 Bolin Gao , Lacra Pavel

We use system-theoretic passivity methods to study evolutionary Nash equilibria learning in large populations of agents engaged in strategic, non-cooperative interactions. The agents follow learning rules (rules for short) that capture…

Computer Science and Game Theory · Computer Science 2024-08-02 Nuno C. Martins , Jair Certório , Matthew S. Hankins

In population games, a large population of players, modeled as a continuum, is divided into subpopulations, and the fitness or payoff of each subpopulation depends on the overall population composition. Evolutionary dynamics describe how…

Optimization and Control · Mathematics 2016-09-19 M. A. Mabrok , Jeff Shamma

In this paper, we consider two-player zero-sum matrix and stochastic games and develop learning dynamics that are payoff-based, convergent, rational, and symmetric between the two players. Specifically, the learning dynamics for matrix…

Machine Learning · Computer Science 2024-09-06 Zaiwei Chen , Kaiqing Zhang , Eric Mazumdar , Asuman Ozdaglar , Adam Wierman

Starting from a heuristic learning scheme for N-person games, we derive a new class of continuous-time learning dynamics consisting of a replicator-like drift adjusted by a penalty term that renders the boundary of the game's strategy space…

Optimization and Control · Mathematics 2014-04-08 Pierre Coucheney , Bruno Gaujal , Panayotis Mertikopoulos

We study the evolutionary dynamics of games under environmental feedback using replicator equations for two interacting populations. One key feature is to consider jointly the co-evolution of the dynamic payoff matrices and the state of the…

Populations and Evolution · Quantitative Biology 2021-05-20 Lulu Gong , Jian Gao , Ming Cao

Continuous-time game dynamics are typically first order systems where payoffs determine the growth rate of the players' strategy shares. In this paper, we investigate what happens beyond first order by viewing payoffs as higher order forces…

Optimization and Control · Mathematics 2013-08-01 Rida Laraki , Panayotis Mertikopoulos

Learning from a partner who collects higher payoff is a frequently used working hypothesis in evolutionary game theory. One of the alternative dynamical rules is when the focal player prefers to follow the strategy choice of the majority in…

Physics and Society · Physics 2018-09-14 Attila Szolnoki , Xiaojie Chen

We consider three distinct discrete-time models of learning and evolution in games: a biological model based on intra-species selective pressure, the dynamics induced by pairwise proportional imitation, and the exponential / multiplicative…

Dynamical Systems · Mathematics 2024-02-27 Fryderyk Falniowski , Panayotis Mertikopoulos

We consider a model of learning and evolution in games whose action sets are endowed with a partition-based similarity structure intended to capture exogenous similarities between strategies. In this model, revising agents have a higher…

Computer Science and Game Theory · Computer Science 2024-07-26 Panayotis Mertikopoulos , William H. Sandholm

This article investigates an evolutionary game based on the framework of interacting particle systems. Each point of the square lattice is occupied by a player who is characterized by one of two possible strategies and is attributed a…

Probability · Mathematics 2015-05-19 N. Lanchier

The commonly used accumulated payoff scheme is not invariant with respect to shifts of payoff values when applied locally in degree-inhomogeneous population structures. We propose a suitably modified payoff scheme and we show both formally…

Physics and Society · Physics 2010-11-24 Leslie Luthi , Marco Tomassini , Enea Pestelacci

The framework of multi-agent learning explores the dynamics of how individual agent strategies evolve in response to the evolving strategies of other agents. Of particular interest is whether or not agent strategies converge to well known…

Computer Science and Game Theory · Computer Science 2023-11-21 Sarah A. Toonsi , Jeff S. Shamma

Replicator dynamics have been widely used in evolutionary game theory to model how strategy frequencies evolve over time in large populations. The so-called payoff matrix encodes the pairwise fitness that each strategy obtains when…

Dynamical Systems · Mathematics 2025-12-23 Haoyu Yin , Xudong Chen , Bruno Sinopoli

A growing number of machine learning architectures, such as Generative Adversarial Networks, rely on the design of games which implement a desired functionality via a Nash equilibrium. In practice these games have an implicit complexity…

Machine Learning · Computer Science 2021-03-08 Gabriel P. Andrade , Rafael Frongillo , Georgios Piliouras

We consider payoff-based learning of a generalized Nash equilibrium (GNE) in multi-agent systems. Our focus is on games with jointly convex constraints of a linear structure and strongly monotone pseudo-gradients. We present a convergent…

Optimization and Control · Mathematics 2025-07-18 Tatiana Tatarenko , Maryam Kamgarpour

In this paper, we focus on studying the passivity properties of different versions of replicator dynamics (RD). RD is an important class of evolutionary dynamics in evolutionary game theory. Evolutionary dynamics describe how the population…

Optimization and Control · Mathematics 2018-12-19 Mohamed Mabrok

This paper investigates the long-term behavior of an interacting particle system of interest in the hot topic of evolutionary game theory. Each site of the $d$-dimensional integer lattice is occupied by a player who is characterized by one…

Probability · Mathematics 2016-06-07 Eric Foxall , Nicolas Lanchier

We report on new stability conditions for evolutionary dynamics in the context of population games. We adhere to the prevailing framework consisting of many agents, grouped into populations, that interact noncooperatively by selecting…

Populations and Evolution · Quantitative Biology 2021-07-08 Semih Kara , Nuno C. Martins
‹ Prev 1 2 3 10 Next ›