Conference Paper

Towards Automatic Personalized Content Generation for Platform Games

Conference: Proceedings of the Sixth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010, October 11-13, 2010, Stanford, California, USA
Source: DBLP


In this paper, we show that personalized levels can be automatically generated for platform games. We build on previous work, where models were derived that predicted player experience based on features of level design and on playing styles. These models are constructed using preference learning, based on questionnaires administered to players after playing different levels. The contributions of the current paper are (1) more accurate models based on a much larger data set; (2) a mechanism for adapting level design parameters to given players and playing style; (3) evaluation of this adaptation mechanism using both algorithmic and human players. The results indicate that the adaptation mechanism effectively optimizes level design parameters for particular players. 1

Download full-text


Available from: Julian Togelius,
  • Source
    • "Ingeniería y Ciencia Alejandro Cannizzo and Esmitt Ramírez game genre [9],[10]. For instance, distinguished examples such as the optimization of tracks in car racing games [11], weapons generation for space shooter games [12], rulesets for board and predator-prey games [13] [14], automatic levels based on playing style for platform games [15],[16], music generation according to the genre or mood of games [17], and others. "
    [Show abstract] [Hide abstract]
    ABSTRACT: we present an approach to create assets using procedural algorithms in maps generation and dynamic adaptation of characters for a MOBA video game, preserving the balancing feature to players. Maps are created based on offering equal chances of winning or losing for both teams. Also, a character adaptation system is developed which allows changing the attributes of players in real-time according to their behaviour, always maintaining the game balanced. Our tests show the effectiveness of the proposed algorithms to establish the adequate values in a MOBA video game.
  • Source
    • "Shaker et al. [4] describe a system for generating playerspecific content for IMB which directly asks questions to the players about their preferences. By contrast, as our system is not designed to generate player-specific content, we do not ask questions to players directly, we ask questions to human workers as a pre-processing step instead. "
    [Show abstract] [Hide abstract]
    ABSTRACT: One of the major challenges in procedural content generation in computer games is to automatically evaluate whether the generated content has good quality. In this paper we describe a system which uses human computation to evaluate small portions of levels generated by an existing system for the game of Infinite Mario Bros. Several such evaluated portions are then combined into a full level of the game. The composition of the small portions into a full level is done by accounting for the human-annotated information and the mathematical model of tension arcs used in interactive drama and storytelling. We tested our system with human subjects and the results show that our approach is able to generate levels with better aesthetics and that are more enjoyable to play than other existing approaches.
    IEEE Conference on Computational Intelligence and Game; 01/2015
  • Source
    • "Player modeling techniques capture information about the player through subjective feedback, in-game activity, or physiological responses [6] and can either be used to report statistics about the players in order to better formulate a fitness evaluation metric or can be used directly to predict whether potential content will be appropriate for the player [25]. As an example, Shaker et al. [26] train neural networks offline to model emotional states of players in a platform game. These models are then used during gameplay to optimize controllable parameters of future maps given the playing style of the player in previous maps. "
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose the strategy of integrating multiple evolutionary processes for personalized procedural content generation (PCG). In this vein, we provide a concrete solution that personalizes game maps in a top–down action-shooter game to suit an individual player's preferences. The need for personalized PCG is steadily growing as the player market diversifies, making it more difficult to design a game that will accommodate a broad range of preferences and skills. In the solution presented here, the geometry of the map and the density of content within that geometry are represented and generated in distinct evolutionary processes, with the player's preferences being captured and utilized through a combination of interactive evolution and a player model formulated as a recommender system. All these components were implemented into a test bed game and experimented on through an unsupervised public experiment. The solution is examined against a plausible random baseline that is comparable to random map generators that have been implemented by independent game developers. Results indicate that the system as a whole is receiving better ratings, that the geometry and content evolutionary processes are exploring more of the solution space, and that the mean prediction accuracy of the player preference models is equivalent to that of existing recommender system literature. Furthermore, we discuss how each of the individual solutions can be used with other game genres and content types.
    IEEE Transactions on Computational Intelligence and AI in Games 01/2014; 7(2):1-1. DOI:10.1109/TCIAIG.2014.2341665 · 1.48 Impact Factor
Show more