Ancient Roman Board Game (ludus-coriovalli.web.app)

A groundbreaking reconstruction of the ancient Roman board game Ludus Coriovalli has been achieved by researchers using artificial intelligence, shedding light on a game lost for over 1,800 years. The study, published in the journal Antiquity, analyzed a carved limestone stone from the Netherlands, revealing geometric wear patterns consistent with gameplay. By employing AI-driven simulations with the Ludii General Game System, the researchers tested various game configurations and identified that the most plausible version involved four Hounds trying to block two Hares. This development is significant for the AI/ML community as it illustrates the potential of AI in historical research, blending modern technology with archaeological findings. The AI simulations ran a thousand rounds per ruleset to uncover the game's mechanics, enabling an authentic re-creation of its strategic elements. Players now can engage with Ludus Coriovalli either against AI or with others, highlighting the flexibility of AI in game design, while also advancing interests in ancient gaming cultures. The convergence of AI technology and historical inquiry opens new avenues for understanding cultural legacies through interactive media.