Students

Identifying the role of attention and cognition within videogame immersion using neuroimaging methods Immersion is a state in which players are engaged to a degree of total absorption that inhibits the ability to correctly report one’s surroundings or time. Present theory on immersion has developed a coherent model that provides sufficient evidence to distinguish itself from other cognitive concepts such as presence, attention, selective attention, absorption and flow....

Using human data to create stronger opponents in Real Time Strategy Games

Use of Artificial General Intelligence techniques, with particular focus on Statistical Forward Planning, for automatic playtesting through the exploration of the skill/strategic space of the game.

Curiosity-driven PhD Candidate in Deep ((Multi-Agent) Reinforcement/Imitation) Learning. Especially interested in (Natural) Language Emergence & Grounding for Human-Machine Cooperation.

I’m interested in generating nonverbal behaviour models for social interactions in VR that builds into an emphatic and engaging virtual human (NPC).

PhD student working on applying rolling horizon evolutionary algorithms to general video game playing, for online planning in video games.

Human-Computer Interaction researcher focusing on what players enjoy about their opponents in strategy games, whether human or AI, and applying that to game design and AI construction.

Software Engineer interested in (both users and AI) behaviour. Working on taking existing AI algorithms and changing their heuristics to have goals that go beyond winning to analyse how agents behave.

Multidisciplinary researcher applying Multiagent Deep Reinforcement learning and Game theory to generate gameplaying AI agents for a wide variety of games.

Improving Game AI Design Using Adversarial Agents This project proposes a novel method for improving the quality of behaviour of human authored agents by pitting them against trained agents and observing what bad behaviours/exploits the trained agents reveal....

Evolving evolvable representations of neural networks

Games industry veteran and researcher with a bridging foot solidly placed in each camp. Gorm currently works on procedural content generation, virtual reality and mixed-initiative co-creative interfaces. He also has an interest in game design, participatory design, game jams and computer graphics.

Applications in game development for programming language theory and AI Modern game development is highly iterative. Iteration is usually discussed in terms of a team completing design iterations, but can also be considered at the level of an individual developer attempting to complete a task, or experimenting with some ideas. At this level, the feedback loop provided by the tool becomes critical. Programming environments in particular often have a very poor feedback loop....

AI for game design: learning from designers For my PhD I am investigating how AI can help developers by learning to generate content in a similar fashion to the developers themselves.  I envision a framework based on reinforcement learning, where an AI can learn a design policy for some content domain (e.g., FPS maps or platformer levels) by observing human designers.  The AI would learn to take particular design actions in certain kinds of content states.  Recent res...

Developing Agents with Human Gameplay Artificial Intelligence has been widely used in video games as agents for non-player characters. This has compelled many researchers to develop and study algorithms and techniques to create agents to compete against humans and defeat them or simply aid them in several tasks. But some have opted for creating agents that have tried to pass the Turing test rather than simply winning....

Deep Learning for Procedural Content Generation in Virtual Environments Ryan Spick is a PhD student with a computer science background, working on methods to improve how content (models, terrain, assets etc.) is created with an autonomous focus, with the main focus on generative deep learning to augment real-world data through a series of neural network layers to learn unlying properties of these data....

Discrete Models and Algorithms to create a more satisfying and strategic opponents For many 4x and Grand Strategy computer games (e.g. Civilisation, Europa Universalis), the player will be playing against one or more AI opponents. For many games, the AI is not clever enough to stand up to a player without being given the ability to "cheat" - ability to spawn in resources, see what the player is doing, etc....