Poster
in
Workshop: GPU-Accelerated and Scalable Optimization (ScaleOpt)

Entropy regularized subgame solving sequential Bayesian games with public actions

Sobhan Mohammadpour ⋅ Samuel Sokota ⋅ Brandon Kaplowitz ⋅ Zico Kolter ⋅ Noam Brown ⋅ Gabriele Farina

Project Page [ OpenReview]

Abstract

Subgame solving is central to scaling equilibrium approximation in large imperfect-information games. We introduce a small set of reusable GPU primitives for high-performance, entropy-regularized subgame solving in public-action Bayesian games (PBGs). Instantiated in Liar’s Dice and Heads-up Hold’em, our approach achieves one to two orders of magnitude speedups and substantially lower memory usage compared to baselines.

Chat is not available.