Search Driven Playtesting of Modern Board Games
A demonstration of how AI can be useful in the game design and development process of a modern board game. By using an artificial intelligence algorithm to play a substantial amount of matches of the board game and collecting data, we can analyze several features of the gameplay as well as of the game board. Results revealed loopholes in the game’s rules and pointed towards trends in how the game is played. We are then led to the conclusion that large scale simulation utilizing artificial intelligence can offer valuable information regarding modern board games and their designs that would ordinarily be prohibitively expensive or time-consuming to discover manually.
AI as Evaluator: Search Driven Playtesting of Modern Board Games
Fernando De Mesentier Silva, Scott Lee, Julian Togelius and Andy Nealen
AAAI 2017 Workshop on What’s Next for AI in Games
Description: Pilot study using the board game Ticket to Ride.
Figure 1: Rule Scenario found by the AIs that is not covered by the rulebook of the game Ticket To Ride. This scenario involves a rule involving face up Train Cards. When 3 or more of the face up Train Cards are wild cards, the face up cards are discarded, and 5 new cards are added. If both players exclusively draw non-wild Train Cards, then at some point, the majority of the deck will consist of wild Train Cards. At some point, the wild cards will appear in the face up set, which will prompt a reshuffle. However, if there are no other cards in the Train Card deck, then the wild cards will reappear in the face up set, prompting another reshuffle. The reshuffle cannot end because there are no other cards in the deck.
Figure 2: A color map of how often a city is claimed by players. A claimed city is one that has at least one route connecting it to an adjacent city claimed by the end of the game. On the map, the darker the city color is, the less desirable it is, meaning, there were more games where no routes connecting to it were claimed.