Towards Finding Flow in Tetris

摘要

One of the most challenging goals in the game industry is to design games which are difficult enough to be a fun challenge but not so hard to provoke frustration among a wide range of different types of players. Dynamic difficulty adjustment (DDA) is a set of techniques used to customize the difficulty of a game according to the skill level of the player so that the game can keep the player 'flowing'. In this paper, we present a novel DDA architecture that we implement using case-based reasoning and we integrate into a Tetris game. In particular, we dynamically change the difficulty of the game by selecting the next piece the player has to place on the board to make the current game more similar to one of the 'good' games in our case base. Games are modeled using time series representing the evolution of different game features and evaluated by the players according to their level of entertainment. This way, we alter the difficulty of the game so that it evolves similarly to other previous good games and we expect the current player also experience the same flow.