Search

The authors would like to thank Juan Ortega and Noor Shaker, as well as all players, for their contributions in creating the dataset. We also thank Robin Baumgarten for making his code publicly available under the WTFPL license. Finally, we would like to thank our reviewers for feedback and suggestions for future work., In this paper we describe a method of modeling play styles as deviations from approximations of game theoretically rational actions. These deviations are interpreted as containing information about player skill and player decision making style. We hypothesize that this information is useful for differentiating between players and for understanding why human player behavior is attributed intentionality which we argue is a prerequisite for believability. To investigate these hypotheses we describe an experiment comparing 400 games in the Mario AI Benchmark testbed, played by humans, with equivalent games played by an approximately game theoretically rationally playing AI agent. The player actions’ deviations from the rational agent’s actions are subjected to feature extraction, and the resulting features are used to cluster play sessions into expressions of different play styles. We discuss how these styles differ, and how believable agent behavior might be approached by using these styles as an outset for a planning agent. Finally, we discuss the implications of making assumptions about rational game play and the problematic aspects of inferring player intentions from behavior., peer-reviewed

Recent advances in emotion and affect recognition can play a crucial role in game technology. Moving from the typical game controls to controls generated from free gestures is already in the market. Higher level controls, however, can also be motivated by player’s affective and cognitive behavior itself, during gameplay. In this paper, we explore player’s behavior, as captured by computer vision techniques, and player’s details regarding his own experience and profile. The objective of the current research is game adaptation aiming at maximizing player enjoyment. To this aim, the ability to infer player engagement and frustration, along with the degree of challenge imposed by the game is explored. The estimated levels of the induced metrics can feed an engine’s artificial intelligence, allowing for game adaptation., This research was supported by the FP7 ICT project SIREN (project no: 258453), peer-reviewed

We present a technology demonstrator for an adaptive serious game for teaching conflict resolution and discuss the research questions associated with the project. The prototype is a single-player 3D mini-game which simulates a resource management conflict scenario. In order to teach the player how to resolve this type of conflict, the underlying system generates level content automatically which adapts to player experience and behaviour. Preliminary results demonstrate the efficiency of the procedural content generation mechanism in guiding the training of players towards targeted learning objectives., This work has been supported, in part, by the FP7 ICT project SIREN (project no: 258453)., peer-reviewed

The authors would like to thank Henrik Jorgensen and all children of Henriette Horlucks and Rosengardskolen Schools, Odense, Denmark that participated in the experiments. The tiles were designed by C. Isaksen from Isaksen Design and parts of their hardware and software implementation were collectively done by A. Derakhshan, F. Hammer, T. Klitbo and J. Nielsen. KOMPAN, Mads Clausen Institute, and Danfoss Universe also participated in the development of the tiles., The notion of constructing a metric of the degree to which a player enjoys a given game has been presented previously. In this paper, we attempt to construct such metric models of children’s ‘fun’ when playing the Bug Smasher game on the Playware platform. First, a set of numerical features derived from a child’s interaction with the Playware hardware is presented. Then the Sequential Forward Selection and the n- Best feature selection algorithms are employed together with a function approximator based on an artificial neural network to construct feature sets and function that model the child’s notion of ‘fun’ for this game. Performance of the model is evaluated by the degree to which the preferences predicted by the model match those expressed by the children in a survey experiment. The results show that an effective model can be constructed using these techniques and that the Sequential Forward Selection method performs better in this task than n-Best. The model reveals differing preferences for game parameters between children who react fast to game events and those who react slowly. The limitations and the use of the methodology as an effective adaptive mechanism to entertainment augmentation are discussed., This work was in part supported by the Danish National Research Council (project no: 274-05-0511)., peer-reviewed