BluffJAX: Adversarial Imperfect Information Games in JAX

BluffJAX is an open‑source suite of adversarial imperfect‑information games implemented in JAX, designed for high‑throughput simulation and GPU parallelization. It includes classic benchmarks like Texas Hold’Em and Kuhn Poker, as well as newer games such as Bluff, Stud Poker, and Kemps, aiming to broaden research in game‑theoretic reinforcement learning. The authors benchmarked throughput, memory usage, and algorithmic performance across single and multi‑GPU setups, showing scalability to hundreds of millions of samples per second and providing baseline results for future work.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• reinforcement-learning
• efficiency
• benchmarks
• safety