MCTS is a strategy that is not widely used on games like Catan, and this paper was able to use it to create a decent AI player. In comparison to humans, it is weak, but the authors plan to implement a better version later. However, skilled human players could consistently beat the AI. During these games, SmartSettlers’ moves were usually the same moves a human would play. SmartSettlers was also tested against humans, notably Istvan Sita–one of the authors of the paper, and a skilled Catan player. SmartSettlers won 49.15% out of all 3-player games, meaning that it was much better than the other computer players. The paper tested the skill of the AI by having it play against other Catan computer players. The AI adjusted the chance for each type of move as it “learned,” but having a baseline chance to work from made the computer player much better. The authors made similar changes for other moves. Due to this, the authors programmed the AI to be 10,000 times more likely to build a settlement than other moves, when that move was possible. One possible move in Catan is to build a settlement, which gives the player 1 point and increases their resource production, making it almost always a good move. These changes made it easier to create an AI player while keeping the game mostly the same.Īlthough Catan has many rules, some parts are simple. Also, SmartSettlers was not allowed to trade with the other players. All cards were made public, instead of some players having hidden development cards. They did this on a modified version of Catan, with simpler rules than the official game. This limited information makes it challenging to create an AI for Catan.Įven so, the authors were able to use the MCTS algorithm in their AI, named SmartSettlers. On top of that, there are elements of randomness, so your actions will not always result in the same outcome.
Players can keep track of the cards other players have, but there are also hidden development cards, so it is not a perfect information game. To play Catan, you must have more than two players. The winner is the first player to reach 10 points, which are mostly gained through building settlements and cities. This is a turn-based game where players gain and trade resource cards to build settlements, cities, and roads. This paper looks at the modern board game Settlers of Catan. Most modern board games don’t have perfect information, and many have random elements. Poker is not a perfect information game since all players have secret cards.
It has normally been used in games where both players have “perfect information.” Chess is a perfect information game since both players can see the entire board. MCTS is an algorithm that works well for games with two players. Although the computer is not aware of what it is doing, this is an example of machine learning. This helps it pick better moves more often. From there, it plays against itself thousands of times before making a move, tallying which move led to more winning games. Using MCTS, the AI chooses a random move to begin. Monte Carlo involves running many simulations of an event to predict a range of possible results. It is based on the Monte-Carlo math technique, named after a famous casino. One strategy for writing an AI is called the Monte-Carlo Tree Search (or MCTS). When an AI is advanced enough to beat the best player in the world at a game like Chess or Go, it’s a huge scientific achievement. However, board games are quite useful when studying AI.
At a glance, board games may seem to have no connection to artificial intelligence (AI).