Tag
This paper investigates design choices for training lightweight reinforcement learning agents in imperfect-information card games, using a fixed rule-based expert as a yardstick for Gin Rummy and Leduc Hold'em. It finds that trust region updates, careful reward design, curriculum learning, warm starting, and checkpoint retention improve performance, while several common techniques like reward shaping and large language model opponents do not help.
This paper investigates learning useful policy representations (embeddings) in two-player zero-sum imperfect-information games, introducing methods for creating policy datasets, learning embeddings, and evaluating them on downstream tasks using Kuhn and Leduc Poker.
This paper introduces MAPLE, a tree search method that aggregates policy and value evaluations from multiple sampled world states, extending AlphaZero to imperfect-information games. Experiments on Phantom Go and Dark Hex show Elo improvements of 291 and 136 over the PIMC-based AlphaZero baseline.
This paper presents a parallelization framework for CFR algorithms using linear algebra operations, achieving up to four orders of magnitude speedup on GPU compared to CPU implementations.