Towards a taxonomy of learning dynamics in 2 x 2 games
Do boundedly rational players learn to choose equilibrium strategies as they play a game repeatedly? A large literature in behavioral game theory has proposed and experimentally tested various learning algorithms, but a comparative analysis of their equilibrium convergence properties is lacking. In this paper we analyze Experience-Weighted Attraction (EWA), which generalizes fictitious play, best-response dynamics, reinforcement learning and also replicator dynamics. Studying $2\times 2$ games for tractability, we recover some well-known results in the limiting cases in which EWA reduces to the learning rules that it generalizes, but also obtain new results for other parameterizations. For example, we show that in coordination games EWA may only converge to the Pareto-efficient equilibrium, never reaching the Pareto-inefficient one; that in Prisoner Dilemma games it may converge to fixed points of mutual cooperation; and that limit cycles or chaotic dynamics may be more likely with longer or shorter memory of previous play.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Taxonomy of Collectible Card Games from a Game-Playing AI Perspective
Collectible card games are challenging, widely played games that have received increasing attention from the AI research community in recent years. Despite important breakthroughs, the field still poses many unresolved c…
Card GamesBench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
The intersection of Mean Field Games (MFGs) and Reinforcement Learning (RL) has fostered a growing family of algorithms designed to solve large-scale multi-agent systems. However, the field currently lacks a standardized…
Reinforcement Learning(Digital) Goodies from the ERC Wishing Well: BabelNet, Babelfy, Video Games with a Purpose and the Wikipedia Bitaxonomy
Game2World Engine: Unlocking In-the-Wild Gameplay Videos for World Model Training
Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-the-wild gameplay videos. However, raw gameplay footage entangles the ga…
Learning in nonatomic games, Part I: Finite action spaces and population games
We examine the long-run behavior of a wide range of dynamics for learning in nonatomic games, in both discrete and continuous time. The class of dynamics under consideration includes fictitious play and its regularized v…