This paper presents a novel approach to automated playtesting for the prediction of human player behavior and experience. We have previously demonstrated that Deep Reinforcement Learning (DRL) game-playing agents can predict both game difficulty and player engagement, operationalized as average pass and churn rates. We improve this approach by enhancing DRL with Monte Carlo Tree Search (MCTS). We also motivate an enhanced selection strategy for predictor features, based on the observation that an AI agent's best-case performance can yield stronger correlations with human data than the agent's average performance. Both additions consistently improve the prediction accuracy, and the DRL-enhanced MCTS outperforms both DRL and vanilla MCTS in the hardest levels. We conclude that player modelling via automated playtesting can benefit from combining DRL and MCTS. Moreover, it can be worthwhile to investigate a subset of repeated best AI agent runs, if AI gameplay does not yield good predictions on average.

This paper presents a review of intrinsic motivation in player modeling, with a focus on simulation-based game testing. Modern AI agents can learn to win many games; from a game testing perspective, a remaining research problem is how to model the aspects of human player behavior not explained by purely rational and goal-driven decision making. A major piece of this puzzle is constituted by intrinsic motivations, i.e., psychological needs that drive behavior without extrinsic reinforcement such as game score. We first review the common intrinsic motivations discussed in player psychology research and artificial intelligence, and then proceed to systematically review how the various motivations have been implemented in simulated player agents. Our work reveals that although motivations such as competence and curiosity have been studied in AI, work on utilizing them in simulation-based game testing is sparse, and other motivations such as social relatedness, immersion, and domination appear particularly underexplored.

In this paper we compare simulator sickness symptoms produced by racing game in three different conditions. In the first experiment the participants played the Need for Speed car racing game with an ordinary 17" display and in the second and third experiments they used a head-worn virtual display for the game playing. The difference between experiments 2 and 3 was in the use of stereoscopy, as in the third experiment the car racing game was seen in stereoscopic three-dimensions. Our results indicated that there were no significant differences in sickness symptoms when we compared the ordinary display and the virtual display in non-stereoscopic mode. In stereoscopic condition the eye strain and disorientation symptoms were significantly elevated compared to the ordinary display. We conclude that using a virtual display as an accessory in a mobile device is a viable alternative, because the non-stereoscopic virtual display did not produce significantly more sickness symptoms compared to ordinary game playing.

This study examines the impact of the display type (form) and content (game) to the PC-game adaptation. An ordinary tabletop display (cathode ray tube; CRT) and a near-eye display (NED) suitable for mobile gaming are compared in two different driving games. A measurement model based on a large dataset (n=2182) is applied to study psychological aspects of the game adaptation. This model integrates two constructs considered important for the game adaptation: involvement and presence. The results show that the content affected the subjective sense of presence. However, the form did not have an effect on the presence. These results indicate that NED's are capable of supporting similar adaptation to the game worlds as compared to CRT's. However, the results also weakly indicate that playing with a CRT increases the evaluations of interaction. The study shows the advantages of using multidimensional measures in studying a rich human-computer interaction.