Enregistré dans:
Détails bibliographiques
Auteurs principaux: Heymann, Benjamin, Lanctot, Marc
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2409.03875
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912393664135168
author Heymann, Benjamin
Lanctot, Marc
author_facet Heymann, Benjamin
Lanctot, Marc
contents When learning to play an imperfect information game, it is often easier to first start with the basic mechanics of the game rules. For example, one can play several example rounds with private cards revealed to all players to better understand the basic actions and their effects. Building on this intuition, this paper introduces {\it progressive hiding}, an algorithm that balances learning the basic mechanics of an imperfect information game and satisfying the information constraints. Progressive hiding is inspired by methods from stochastic multistage optimization, such as scenario decomposition and progressive hedging. We prove that it enables the adaptation of counterfactual regret minimization to games where perfect recall is not satisfied. Numerical experiments illustrate that progressive hiding produces notable improvements in several settings.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03875
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning in Games with Progressive Hiding
Heymann, Benjamin
Lanctot, Marc
Computer Science and Game Theory
When learning to play an imperfect information game, it is often easier to first start with the basic mechanics of the game rules. For example, one can play several example rounds with private cards revealed to all players to better understand the basic actions and their effects. Building on this intuition, this paper introduces {\it progressive hiding}, an algorithm that balances learning the basic mechanics of an imperfect information game and satisfying the information constraints. Progressive hiding is inspired by methods from stochastic multistage optimization, such as scenario decomposition and progressive hedging. We prove that it enables the adaptation of counterfactual regret minimization to games where perfect recall is not satisfied. Numerical experiments illustrate that progressive hiding produces notable improvements in several settings.
title Learning in Games with Progressive Hiding
topic Computer Science and Game Theory
url https://arxiv.org/abs/2409.03875