Researchers have used artificial intelligence to model possible rulesets for a Roman board game, concluding it was a kind of game previously unknown in Europe until the Middle Ages, pushing back evidence of their play by several centuries.
Board games have been played by almost all cultures since at least the Bronze Age, but many games in the past were ephemeral, drawn onto the ground and played with sticks and stones, meaning they do not survive archaeologically.
Therefore, the discovery of a possible stone game board at the Roman town of Coriovallum in present-day Heerlen, the Netherlands (stored in Het Romeins Museum in Heerlen), provides an exciting opportunity to explore the archaeology of play.
“We identified the object as a game because of the geometric patten on its upper face and because of evidence that it was deliberately shaped”, says lead author of the research, Dr Walter Crist from Leiden University. “Further evidence that it was a game was presented by visible damage on the surface that would be consistent with abrasion caused by sliding Roman-era game pieces on the surface.”
However, it does not match the form of any other game that has been documented.
To determine whether the object was in fact a board game, Dr Crist and a team of researchers from several institutions in the Netherlands, Belgium and Australia used artificial intelligence to simulate possible rulesets based on the use wear on the object.
“The damage was unevenly distributed along the lines of the board”, explains Crist. “We sought to answer the question of whether we could use AI-driven simulated play as a tool to discover playing rules that would replicate this disproportionate pattern of use wear on the surface of this board with rules similar to those documented for other small games in Europe, thus confirming that the object was likely to have been a game board.”
Using the AI-driven play system Ludii, the researchers made two AI agents play against each other using the object as a board, utilising rulesets from many ancient board games documented in Europe, such as haretavl from Scandinavia and gioco dell’orso from Italy.
They found that the use wear on the object is consistent with the playing of blocking games: board games in which the goal is to block the opponent from moving.
Importantly, evidence for blocking games is incredibly rare in Europe and only documented from the Middle Ages onwards. The study indicates not only that the object was indeed a Roman board game but also pushes the evidence for the playing of blocking games in Europe back several centuries.
It also has significant implications for the study of ancient board games going forward.
“This is the first time that AI-driven simulated play has been used in concert with archaeological methods to identify a board game”, Crist concludes. “This research provides archaeologists with the tools to be able to identify games from ancient cultures that are unusual or uncommonly played, since current methods for identification rely on connecting the geometric patterns that make up the playing surface to games that are known today from references in text, or from artistic representations of them.”
The research was funded by the Digital Ludeme Project (ERC Consolidator grant #771292) led by Cameron Browne and improved by European Cooperation in Science and Technology (COST) Action #CA22145 Computational Techniques for Tabletop Games Heritage (GameTable).