Publications

DEFCON is a nuclear war simulation strategy game released in 2006 by Introversion Software Ltd. We describe an approach to simulating human game-play using a variety of AI techniques, including simulated annealing, decision tree learning and case-based reasoning. We have implemented an AI-bot that uses a novel approach to planning fleet movements and attacks. This retrieves plans from a case base of previous games, then merges these using a method based on decision tree learning. In addition, we have implemented more sophisticated control over low-level actions such as firing missiles and guiding planes. In particular, we have written routines to enable the AI-bot to synchronise bombing runs, and enabled a simulated annealing approach to assigning bombing targets to planes and opponent cities to missiles. We describe how our AI-bot operates, and the experimentation we have performed in order to determine an optimal configuration for it. With this configuration, our AIbot beat Introversion’s finite state machine automated player in 76.7% of 150 matches played.

The invention of mixed reality games that combine virtual and physical play offers a rich and challenging application area for AI techniques. We look at the possibility of using descriptive machine learning to automatically invent simple mixed reality games. Specifically, we demonstrate that the HR learning system can generate coherent domain knowledge from the noisy play data gathered from a number of simple physical games. We describe how this could be used to support mixed reality game invention, and discuss the prospects for further work in this area.

Behaviour trees provide the possibility of improving on existing Artificial Intelligence techniques in games by being simple to implement, scalable, able to handle the complexity of games, and modular to improve reusability. This ultimately improves the development process for designing automated game players. We cover here the use of behaviour trees to design and develop an AI-controlled player for the commercial real-time strategy game DEFCON. In particular, we evolved behaviour trees to develop a competitive player which was able to outperform the game’s original AI-bot more than 50% of the time. We aim to highlight the potential for evolving behaviour trees as a practical approach to developing AI-bots in games.

The automated classification of player behaviour and a subsequent adaptation of game rules in video games is an area of research of interest to both the games industry and to academia, requiring a combination of AI, HCI, psychology, statistics, data mining and machine learning. In this paper, we describe an experiment to answer the question whether it is possible to measure and distinguish behaviour of a player playing a simple game with very limited inputs and a limited variety of possible actions. We use the arcade style action game PacMan to record a variety of game-related metrics in an online survey comprised of 245 players, each playing 5 sessions of PacMan. Then, the resulting data is analysed using discretization methods and linear discriminant analysis. The results indicate that differentiation between different players and different playing styles is possible, and that the methods used are suitable to automatically identify the most significant distinguishing features of player behaviour.

This paper describes the 2009 Mario AI Competition, which was run in association with the IEEE Games Innovation Conference and the IEEE Symposium on Computational Intelligence and Games. The focus of the competition was on developing controllers that could play a version of Super Mario Bros as well as possible. We describe the motivations for holding this competition, the challenges associated with developing artificial intelligence for platform games, the software and API developed for the competition, the competition rules and organization, the submitted controllers and the results. We conclude the paper by discussing what the outcomes of the competition can teach us both about developing platform game AI and about organizing game AI competitions. The first two authors are the organizers of the competition, while the third author is the winner of the competition.

In the commercial video game industry, computer opponents that act intelligently are increasingly important, especially as better graphical effects decline to serve as a driving force for the commercial success of a game. The methods used by developers to create these bots are often obsolete and struggle to scale with the complexity of modern games. Nonetheless the use of modern artificial intelligence techniques used by researchers is rarely seen in video games. In this project, we designed and implemented a computer opponent for the real- time strategy game DEFCON by combining artificial intelligence methods such as case-based reasoning, decision tree algorithms and hierarchical planning. High-level strategy plans for matches are automatically created by querying a case base of recorded matches and building a plan decision tree. The development of an automated opponent for a complex video game required the application of many different techniques to receive, store, process and predict game information. For this purpose, alongside a high-level reasoning system, we use secondary AI techniques like simulated annealing and influence mapping to create a reactive and learning bot. We applied these techniques in DEFCON and created a competitive bot that can beat the AI bot developed by Introversion consistently. The importance of small-scale tactics in this game requires careful unit control, which we incorporated through various methods, such as a movement desire model, fleet formations and a synchronous attack algorithm. Extensive testing was conducted to optimise and fine-tune the efficiency of these optimisation algorithms. Comprehensive training of high-level plans enabled our bot to learn potent strategies that provided a win ratio of over 75% against the official AI bot developed for DEFCON by Introversion.