paper-with-me

Papers

Best-response dynamics, playing sequences, and convergence to equilibrium in random games

2021-01-11 · Torsten Heinrich, Yoojin Jang, Luca Mungo, Marco Pangallo, Alex Scott, Bassel Tarbush, Samuel Wiese

We analyze the performance of the best-response dynamic across all normal-form games using a random games approach. The playing sequence -- the order in which players update their actions -- is essentially irrelevant in determining whether the dynamic converges to a Nash equilibrium in certain classes of games (e.g. in potential games) but, when evaluated across all possible games, convergence to equilibrium depends on the playing sequence in an extreme way. Our main asymptotic result shows that the best-response dynamic converges to a pure Nash equilibrium in a vanishingly small fraction of all (large) games when players take turns according to a fixed cyclic order. By contrast, when the playing sequence is random, the dynamic converges to a pure Nash equilibrium if one exists in almost all (large) games.

📄 PDF Abstract BibTeX arXiv:2101.04222

Code (0)

등록된 구현이 없습니다.

Tasks

All

Similar Papers 제목 키워드 기반

Fictitious play in zero-sum stochastic games

2020-10-08 · Muhammed O. Sayin, Francesca Parise, Asuman Ozdaglar

We present a novel variant of fictitious play dynamics combining classical fictitious play with Q-learning for stochastic games and analyze its convergence properties in two-player zero-sum stochastic games. Our dynamics…

Q-Learning

Independent Learning in Stochastic Games

2021-11-23 · Asuman Ozdaglar, Muhammed O. Sayin, Kaiqing Zhang

Reinforcement learning (RL) has recently achieved tremendous successes in many artificial intelligence applications. Many of the forefront applications of RL involve multiple agents, e.g., playing chess and Go games, aut…

Autonomous DrivingReinforcement Learning (RL)

Fast computation of Nash Equilibria in Imperfect Information Games

2020-01-01 · ICML 2020 1 · Remi Munos, Julien Perolat, Jean-Baptiste Lespiau, Mark Rowland 외

We introduce and analyze a class of algorithms, called Mirror Ascent against an Improved Opponent (MAIO), for computing Nash equilibria in two-player zero-sum games, both in normal form and in sequential imperfect inform…

Form

Learning in games via reinforcement and regularization

2014-07-23 · Panayotis Mertikopoulos, William H. Sandholm

We investigate a class of reinforcement learning dynamics where players adjust their strategies based on their actions' cumulative payoffs over time - specifically, by playing mixed strategies that maximize their expecte…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Best Response Convergence for Zero-sum Stochastic Dynamic Games with Partial and Asymmetric Information

2025-01-10 · Yuxiang Guan, Iman Shames, Tyler H. Summers

We analyze best response dynamics for finding a Nash equilibrium of an infinite horizon zero-sum stochastic linear quadratic dynamic game (LQDG) with partial and asymmetric information. We derive explicit expressions for…