Intelligent Games and Game Intelligence

Research subject: Computational Intelligence and Game Balance

Game design has been a staple of human ingenuity and innovation for as long as games have been around. From sports, such as football, to applying game mechanics to the real world, such as reward schemes in shops, games have impacted the world in surprising ways. This process can, and should, be aided by automated systems, as machines have proven to be capable of finding innovative ways to complement human intuition and inventiveness. When man and machine cooperate, better products are created and the world has only to benefit. My research seeks to find, test and assess methods to apply computational intelligence to human-led game balance. Early research has proven that AI can successfully aid game designers in analysing the viability of various game rules and I intend to document this and polish the techniques that will result from my work. To achieve this, I am making use of cutting edge algorithms, powerful AI techniques and novel methods. Most of the current work done involves the use of evolutionary algorithms, as well as statistical analysis and evaluation of intelligent agents in various video games.

The topic changed a bit from the original idea of diplomatic AI, but there is no regret. The change came naturally, as, through pure luck, a lot of the tools I developed for the previous subject fit smoothly with the new one. And while I still want to research AI and diplomacy, it will have to wait until it has more industry impact.

Publications

Evolving a Designer-Balanced Neural Network for Ms PacMan - Accepted for publication at CEEC 2017

Speeding up genetic algorithm-based game balancing using fitness predictors - poster presented at GECCO 2017

Automated Game Balancing in Ms Pacman and StarCraft using Evolutionary Algorithms - EvoStar 2017