Home > Research > Publications & Outputs > Best-response Dynamics in Zero-sum Stochastic G...

Electronic data

Links

Text available via DOI:

View graph of relations

Best-response Dynamics in Zero-sum Stochastic Games

Research output: Contribution to journalJournal articlepeer-review

Published
Close
Article number105095
<mark>Journal publication date</mark>1/09/2020
<mark>Journal</mark>Journal of Economic Theory
Volume189
Number of pages31
Publication StatusPublished
Early online date16/07/20
<mark>Original language</mark>English

Abstract

We define and analyse three learning dynamics for two-player zero-sum discounted-payoff stochastic games. A continuous-time best-response dynamic in mixed strategies is proved to converge to the set of Nash equilibrium stationary strategies. Extending this, we introduce a fictitious-play-like process in a continuous-time embedding of a stochastic zero-sum game, which is again shown to converge to the set of Nash equilibrium strategies. Finally, we present a modified δ-converging best-response dynamic, in which the discount rate converges to 1, and the learned value converges to the asymptotic value of the zero-sum stochastic game. The critical feature of all the dynamic processes is a separation of adaption rates: beliefs about the value of states adapt more slowly than the strategies adapt, and in the case of the δ-converging dynamic the discount rate adapts more slowly than everything else.