Learning in Games with Progressive Hiding

TL;DR

This paper introduces progressive hiding, an algorithm that improves learning in imperfect information games by balancing understanding game mechanics and respecting information constraints, inspired by stochastic optimization methods.

Contribution

It presents a novel algorithm, progressive hiding, enabling counterfactual regret minimization in non-perfect recall games, with theoretical and empirical validation.

Findings

Improves learning efficiency in imperfect information games.

Enables counterfactual regret minimization without perfect recall.

Shows notable performance gains in numerical experiments.

Abstract

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.