Entropy regularized subgame solving sequential Bayesian games with public actions
Sobhan Mohammadpour · Samuel Sokota · Brandon Kaplowitz · Zico Kolter · Noam Brown · Gabriele Farina
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.
Successful Page Load