Team Sports for Game AI Benchmarking Revisited

Sport games are among the oldest and best established genres of computer games. Sport-inspired environments, such as RoboCup, have been used for AI benchmarking for years. We argue that, in spite of the rise of increasingly more sophisticated game genres, team sport games will remain an important testbed for AI benchmarking due to two primary factors. First, there are several genre-specific challenges for AI systems that are neither present nor emphasized in other types of games, such as team AI and frequent replanning. Second, there are unmistakable nonskill-related goals of AI systems, contributing to player enjoyment, that are most easily observed and addressed within a context of a team sport, such as showing creative and emotional traits. We analyze these factors in detail and outline promising directions for future research for game AI benchmarking, within a team sport context.

Play more, enjoy more, keep playing; rugby is a simple game

Drop out and attrition rates in youth sport are well-documented in the literature. Research has found that children overwhelmingly state that enjoyment, fun, and positive experiences are the primary reasons to participate in sport. Competitive Engineering (CE) is a structurally-based competitive climate process designed to create a more positive experience in youth sport. CE encompasses changes to league structures, equipment, pitch-size, and game rules. For example, rule changes that stipulate greater involvement (e.g., playing time) or action (e.g., increasing scoring opportunities) are designed to improve engagement. Despite this, few studies have examined whether CE-based rule changes influence factors known to influence drop out from sport. The aim of this study was to assess the impact of a rule change in youth rugby whereby any player selected as part of a match day squad must play at least half a game or equivalent (i.e., the ‘Half-Game Rule’). To achieve this, we studied the influence of the rule change on player reported outcomes throughout the 2017/2018 playing season. Players who “always or almost always” experienced playing at least half a game more often than other players; reported higher enjoyment, than those who played less regularly ( F = 35.6, P < .001). Importantly, players who reported higher levels of enjoyment also reported greater intentions to continue playing rugby ( F = 6.4, P < .002). Findings support the use of CE to facilitate player enjoyment in team sports and could lead to reduced attrition in youth sport more generally.

Acceptance of Virtual Reality Games

As virtual reality (VR) games are getting more widespread, the need to understand the interaction between players and the VR games is gaining prominence. The present study examines player endorsement of virtual reality games from an amalgamation of technology acceptance, self-determination, and flow theory perspectives. A survey was carried out with participants (N = 396) who had played a VR game at least once and at most five times. Structural equation modeling analyses showed that perceived ease of use was the primary predictor for satisfaction of self-determination constructs (autonomy and competence) and flow constructs (immersion and concentration), which in turn predicted player enjoyment. Accordingly, the results suggest the importance of including self-determination constructs in addition to the flow perspective within the context of technology acceptance model, for explaining the acceptance of VR gaming. Findings also showed that enjoyment resulted in positive attitudes towards VR gaming, and these attitudes predicted intention to play VR games.

Modeling Gameplay Enjoyment, Goal Orientations, and Individual Characteristics

The purpose of this study was to investigate the relationships between gameplay enjoyment, gaming goal orientations, and individual characteristics. A total of 301 participants were surveyed and the data were analyzed using structural equation modeling. This led to an expanded Gameplay Enjoyment Model (GEM) with 41 game design features that influence player enjoyment. Furthermore, a 3x2 Gaming Goal Orientations model was established with six dimensions that describe players' motivations for gaming. In addition, players' individual characteristics were used to predict gameplay enjoyment in the GEM-Individual Characteristics model. The six Gaming Goal Orientations dimensions were the strongest predictors, while the commonly used gender and hours played per week variables failed to predict enjoyment. The results of this study enable important work to be conducted surrounding gameplay experiences and individual characteristics. Ultimately, it is believed that the Gameplay Enjoyment Model, Gaming Goal Orientations, and the GEM-Individual Characteristics model will be useful tools for researchers and designers who seek to create effective gameplay experiences that meet the needs of players.

A Review of Real-Time Strategy Game AI

This literature review covers AI techniques used for real-time strategy video games, focusing specifically on StarCraft. It finds that the main areas of current academic research are in tactical and strategic decision-making, plan recognition, and learning, and it outlines the research contributions in each of these areas. The paper then contrasts the use of game AI in academia and industry, finding the academic research heavily focused on creating game-winning agents, while the indus- try aims to maximise player enjoyment. It finds the industry adoption of academic research is low because it is either in- applicable or too time-consuming and risky to implement in a new game, which highlights an area for potential investi- gation: bridging the gap between academia and industry. Fi- nally, the areas of spatial reasoning, multi-scale AI, and co- operation are found to require future work, and standardised evaluation methods are proposed to produce comparable re- sults between studies.