[2506.22609] Ludax: A GPU-Accelerated Domain Specific Language for Board Games

Computer Science > Artificial Intelligence arXiv:2506.22609 (cs) [Submitted on 27 Jun 2025 (v1), last revised 25 Mar 2026 (this version, v2)] Title:Ludax: A GPU-Accelerated Domain Specific Language for Board Games Authors:Graham Todd, Alexander G. Padula, Dennis J.N.J. Soemers, Julian Togelius View a PDF of the paper titled Ludax: A GPU-Accelerated Domain Specific Language for Board Games, by Graham Todd and 3 other authors View PDF HTML (experimental) Abstract:Games have long been used as benchmarks and testing environments for research in artificial intelligence. A key step in supporting this research was the development of game description languages: frameworks that compile domain-specific code into playable and simulatable game environments, allowing researchers to generalize their algorithms and approaches across multiple games without having to manually implement each one. More recently, progress in reinforcement learning (RL) has been largely driven by advances in hardware acceleration. Libraries like JAX allow practitioners to take full advantage of cutting-edge computing hardware, often speeding up training and testing by orders of magnitude. Here, we present a synthesis of these strands of research: a domain-specific language for board games which automatically compiles into hardware-accelerated code. Our framework, Ludax, combines the generality of game description languages with the speed of modern parallel processing hardware and is designed to fit neatly into...