From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

by   Julien Perolat, et al.

In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting the reward (by adding a regularization term) of the game can give strong convergence guarantees in monotone games. We continue by showing how this reward adaptation technique can be leveraged to build algorithms that converge exactly to the Nash equilibrium. Finally, we show how these insights can be directly used to build state-of-the-art model-free algorithms for zero-sum two-player Imperfect Information Games (IIG).



Vaclav Kosar

Listen to the paper here you can 👂📰🤓  From Poincaré Recurrence to Convergence in Imperfect Information Games - To build model-free algorithms for zero-sum games this paper generalize existing results of Poincare recurrence.


page 1

page 2

page 3

page 4


Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game

Creating strong agents for games with more than two players is a major o...

Computing Nash Equilibria in Multiplayer DAG-Structured Stochastic Games with Persistent Imperfect Information

Many important real-world settings contain multiple players interacting ...

Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall

We study the problem of learning a Nash equilibrium (NE) in an imperfect...

Limited Lookahead in Imperfect-Information Games

Limited lookahead has been studied for decades in complete-information g...

Joint Policy Search for Multi-agent Collaboration with Imperfect Information

To learn good joint policies for multi-agent collaboration with imperfec...

Sound Search in Imperfect Information Games

Search has played a fundamental role in computer game research since the...

Bayesian Opponent Exploitation in Imperfect-Information Games

Two fundamental problems in computational game theory are computing a Na...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.