< Back Rokas Volkovas Queen Mary University of London iGGi Alum Application of Neuroevolution to General Video Game Playing In the field of artificial intelligence, great advancements in developing AI capable of playing specific games has been made over last few decades. Over the years, the potential of General Game Playing (GGP) AI, was realized, and thus a new area of research was spawned, focusing mainly on turn-based board games. Rapidly expanding, it was just recently extended to include video games and has morphed into General Video Game Playing (GVGP). The studies in this space of AI are highly attractive due to their solution capacity of being highly transferable. As the field is relatively new, there are many different paths to explore. Some effort has already been put into incorporating the established Genetic Algorithm techniques into the area. The goal of the proposed research is to further develop models using the more complex evolutionary algorithms to find generalist solutions to the problems exposed in GVGP. More specifically, the research will aim to discover the appropriate applications and the modifications necessary of approaches such as Competitive Coevolution, circumventing its drawbacks and evolving populations capable of playing multiple games. Furthermore, in addition to other methods it will be concerned with the application of models developing generalist memory on a slower scale evolution (compared to individual in a population) with continuous state perturbations, to find closer to optimum results - adapting networks of individuals to the fitness landscape. In order to reach the goals of the research a number of experiments will be conducted, using a select few video games as a base performance measure. Training the populations evolved will involve tuning the evolutionary operators as well as altering pre-designed system be- haviours to suitably compare the viability of applied procedures. The success of bridging EA with GVPG, along with its advantages and drawbacks in the field will be readily deter- mined, comparing the solutions found to those of other existing approaches. Specifically, the similarity of the behaviour in evolvability using genetic networks searching for solutions and learning theory, via neural networks, has recently been suggested. Evolution is defined to not have any foresight, but models were built showing how it can remember previously discovered solutions, which would imply that natural selection leans towards long term evolvability. Kostas Kouvaris et. al. further establishes the underlying equivalence of the approaches, applying machine learning techniques to improve the generalisation of EA. The generalization allows combining the features from previous experience to find individuals with new feature combinations, better adapted to unseen environments. Were the exploratory learning methods developed in EA to perform no less satisfactorily in the gaming industry environment, given enough sample data from a handful of well defined behaviours, the AI units could be trained to adapt to the new levels they are placed in. In theory, this would then translate to the same amount of effort producing a larger variety of content or, alternatively, producing the same amount of content with less effort, distributing the excess to other areas of development or eliminating it to lower the total production cost. Rokas is an MEng Electronic Engineering graduate from University of Southampton. Initially, pushed away from programming in school due to being taught Pascal, he realized its power in the compulsory C course in University. Applying the knowledge to building games caused the gradual shift from electronics to software development, with the 4th year modules all having the CS tag. During the undergraduate studies Rokas held the UKESF scholarship and did 2 summer internships at Imagination Technologies. Interests in game and software development got him researching neuroevolutionary machine learning for video games. Please note: Updating of profile text in progress Email Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Automatic Game Tuning for Strategic Diversity Practical Game Design Tool: State Explorer Extracting learning curves from puzzle games Mek: Mechanics prototyping tool for 2d tile-based turn-based deterministic games Diversity maintenance using a population of repelling random-mutation hill climbers Themes Game AI - Previous Next

< Back Tania Dales University of York iGGi PG Researcher Available for placement Tania is an indie video game designer and developer, working with horror, science fiction and games which are a little strange, bizarre and uncomfortable. About Tania's research: "My research explores the relationship between humanoid character design and existential horror in video games. I adopt a mixed methods approach, investigating existing games, designer interviews and player surveys, along with a research-through-design methodology, reflecting on the practice of character design. The core games I am exploring incorporate themes of existential horror, identity, self, and human existence. In video games with horror themes, non-playable characters (NPCs) are often used to prompt a reaction from the player, and it isn’t always fear. There are often times when the NPC isn’t acting in an outwardly threatening way, yet it still causes us to become unsettled. My research explores unsettling NPCs that incorporate themes of existential horror." Email tania.dales@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor: Dr Ben Kirman Themes Design & Development Game AI Immersive Technology Player Research - Previous Next

< Back Dr Martin Balla Queen Mary University of London iGGi Alum Before starting his PhD Martin studied Computer Science at the University of Essex. His main interest is artificial intelligence and its application to all sort of problems ranging from computer vision to game AI. He likes spending his spare time with various activities which mainly involves reading, playing video games and skateboarding. Martin's PhD thesis focuses on Reinforcement Learning agents that can adapt to changes in the reward function and/or changes in the environment. His work investigates how agents can transfer their knowledge to changes in the environment, such as new rewards, levels or visuals. Outside of his main research direction, Martin is involved with the Tabletop games framework (TAG), which is a collection of various tabletop games implemented with a common API with a focus on various game-playing agents (including RL). TAG brings various challenges to RL agents compared to search-based agents, such as complex action spaces, unique observation spaces (various embeddings), multi-agent dynamics with competitive and collaborative aspects, and lots of hidden information and stochasticity. Email m.balla@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Diego Pérez-Liébana Prof. Simon Lucas Featured Publication(s): Multi-task Reinforcement Learning for Adaptive Agents Program Committee and Subreviewers Tiny Moves: Game-based Hypothesis Refinement PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games TAG: Pandemic Competition Task Relabelling for Multi-task Transfer using Successor Features TAG: A tabletop games framework Design and implementation of TAG: a tabletop games framework Evaluating generalisation in general video game playing Evaluating Generalization in General Video Game Playing Analysis of statistical forward planning methods in Pommerman Themes Game AI - Previous Next

< Back Dr Cristina Guerrero-Romero Queen Mary University of London iGGi Alum Cris is a versatile Software Engineer with four years of experience in web development across different areas of the tech stack. She studied Software and Computer Engineering at Universidad Autónoma de Madrid (Spain) and is currently completing her PhD at Queen Mary University of London (QMUL); during which she has done two internships at Google. Her research ‘Beyond Playing to Win: Broadening the Study and Use of Gameplaying Agents when Provided with Distinct Behaviours’ is focused on expanding the research on game-playing agents beyond the objective of winning at them. She looks at 1) broadening the scope by diversifying agents goals and heuristics; 2) broadening the vision by proposing a team of agents to assist game development; 3) broadening the usage by eliciting diverse automated gameplay, and 4) broadening the horizon by analysing the strengths of the agents from a Player Experience perspective instead of their performance. Cris is passionate about solving problems and learning. Outside of her work, she enjoys playing video games and TTRPGs. Random facts are that Portal and TLOU are two of her favourite game series and her chosen superpower would be teleportation. Please note: Updating of profile text in progress Email Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Beyond Playing to Win: Elicit General Gameplaying Agents with Distinct Behaviours to Assist Game Development and Testing Beyond Playing to Win: Creating a Team of Agents with Distinct Behaviours for Automated Gameplay MAP-Elites to Generate a Team of Agents that Elicits Diverse Automated Gameplay Generating Diverse and Competitive Play-Styles for Strategy Games Studying General Agents in Video Games from the Perspective of Player Experience Ensemble Decision Systems for General Video Game Playing Using a Team of General AI Algorithms to Assist Game Design and Testing Beyond playing to win: Diversifying heuristics for GVGAI Themes Design & Development Game AI - Previous Next

< Back Dien Nguyen Queen Mary University of London iGGi PG Researcher Available for placement I graduated from the University of California, Irvine with a BSc in Computer Game Science where I became interested in the intersection of games and artificial intelligence – applying search, planning, evolutionary methods and knowledge representation to game playing and game design. My long-term goal is to work on the problem of formalizing game elements, representing game systems in a way that allows for automatic reasoning and inference. I also enjoy playing games where I can customize and theorycraft my playstyle to satisfy certain gameplay fantasies while beating the game. My current research is within the field of Automated Game Design Learning, an emerging field in AI research with the purpose of learning game design models through playing. The current strategy is to play out the full game in thousands of iterations, which can be impractical for complex games with large state space and computationally expensive forward models. My research will focus on applying Go-Explore—a recent exploration paradigm that outperforms many state-of-the-arts—to improve the efficiency of automated playtesting of tabletop games by using an archive of interesting game states to reduce the time needed for self-play. The research will be primarily conducted within the TAG framework and aim to be game-agnostic. On successful completion, this research will improve game development cycles, resulting in higher-quality games, and potentially give unique insights into the game design process. Email d.l.nguyen@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor: Dr Diego Pérez-Liébana Featured Publication(s): Game-Agnostic Value Functions through Automatic JSON Feature Extraction JSON-Bag: A generic game trajectory representation Unveiling modern board games: an ML-based approach to BoardGameGeek data analysis Themes Applied Games Creative Computing Design & Development Game AI - Previous Next

< Back Dr Jen Beeston University of York iGGi Alum + Supervisor Jen is currently working as a Lecturer in HCI in the Department of Computer Science (University of York) whilst writing up her PhD. She has a multidisciplinary background, from studying subjects such as environmental science and media production and having worked in various jobs such as grassland research, flood risk management, and plasterboard quality. She feels extraordinarily fortunate to have been able to do research into her lifelong hobby of playing digital games. In particular, Jen feels it is important that everyone has the opportunity to enjoy gaming should they wish. As such, her research has been aimed at exploring the experiences of people with disabilities in playing games, beyond how various technologies can support play. Jen’s research is focused particularly on the social experiences of players with disabilities in-game and within the broader gaming community. She has worked alongside the charity AbleGamers with the aims of investigating these player’s experiences of gaming, what effects alternative controls have upon play, and what it’s like for these players in multiplayer or online games. Jen is broadly interested in HCI, user experience, player experience, inclusivity, social play, and game communities. Outside of her work, she enjoys walking, thinking, reading, crochet, art, and tabletop roleplaying games. Email jen.beeston@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Validation and Prioritization of Design Options for Accessible Player Experiences Social experiences of people with disabilities in playing (in) accessible digital games Enabled players: The value of accessible digital games Accessible player experiences (APX): The players Characteristics and motivations of players with disabilities in digital games Perceptions of Telepresence Robot Form Themes Accessibility - Previous Next

< Back Dr Mike Cook Supervisor Mike is a Senior Lecturer at King's College London where he leads research into automated game design, computational creativity, and the theory and practice of generative systems. Email mike@possibilityspace.org Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Creative Computing Design & Development Game AI - Previous Next

< Back Luke Farrar University of York iGGi Alum Luke Farrar is an iGGi PhD student at The University of York undertaking research in Flexible and Realistic Character Animations in Complex and Dynamic Environments. Luke's research focuses through his bachelor's and master's degrees were on applying machine learning to interesting and unique settings. In his bachelor's he focused on creating an application for individuals that suffered from cognitive impairments through the use of the "Microsoft HoloLens" and machine learning to allow those individuals to maintain a semblance of everyday life. In his postgraduate Luke focused on using machine learning to generalise high-fidelity scientific simulations to rapidly generate predictions for parameter combinations that had not yet been sampled in order to accelerate the production of new results. Luke revels in all things AI, knowing that there is always more to learn and seeks to continually deepen his understanding around AI. A description of Luke's research: Modern games have an increasing focus on hyper-realism and immersion to better capture the attention of players. One of the ways that games can break this immersion is by having animations that break the flow of movement or actions through the use of predefined animations. Motion matching is a solution for predicting the best next frame of an animation by looking at the pose and user trajectory. The downside however, is that when you increase the amount of possible animations in the database the runtime cost also increases. A solution was proposed known as 'learned motion matching' (Holden et al., 2020) which takes the positive properties of motion matching but also achieves the scalability of neural-network-based generative models. This project will explore and improve the learned motion matching method through implementation of memory layers to improve accuracy without the sacrifice of increasing runtime costs. A restructuring and adaptation of the existing machine learning neural network used could also improve the learned motion matching method as breaking down each step of the learned motion matching at each step could uncover optimisations that are not initially visible. Another way restructuring could improve the learned motion matching is through creating a more succinct all-in-one approach which may streamline the process. Email lukebfarrar@gmail.com Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Miles Hansard Dr Patrik Huber Dr James Walker Themes Immersive Technology - Previous Next

< Back Prof. Alex Wade University of York Supervisor Alex Wade is a psychologist working in the field of human cognitive neuroscience. He uses a combination of structural and functional brain imaging, electrophysiology, psychophysics and big data analysis to ask how we see, solve problems and make decisions. His most recent work in the domain of video games focuses on what we can learn about global cognitive health and player personality from the analysis of large MOBA datasets in collaboration with Riot games (League of Legends). He is particularly interested in supervising students with a psychology or neuroscience background in the areas of: Using commercial video games to measure cognition and personality How the brain responds to solo- and group gameplay Can we use video games to monitor and modify real-world cognition, behaviour and mental health Research themes: Game Analytics Games with a Purpose Computational Creativity E-Sports Player Experience The neuroscience of gaming Email alex.wade@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Applied Games Creative Computing Esports Game Data Player Research - Previous Next

< Back Dr Matthew Whitby University of York iGGi Alum Matthew Whitby is a games designer, and player experience academic investigating how games can shape our perspectives on a small or grand scale. In particular, his work considers how we can make the development of perspective challenging processes easier for game developers. Previously, Matthew has published his undergraduate dissertation within the Games Journal, which explored the creation and design of Games Installations. Games that make full use of their surrounding space, and in fact incorporate the real world with its digital counterpart. In addition, he’s worked with Motek Medical, a rehabilitation company based in Amsterdam, where he developed socially focused multiplayer applications. More recently, he attended CHI Play 2019 to present the foundational study of his PhD titled: “One of the Baddies All Along: Perspective Challenging Moments in Games”. He continues to develop this idea forward, while developing games (both digital and table-top) in his spare time. Matthew’s work hopes to answer; how games can challenge a player’s perspective, and if this is a phenomenon that can be intentionally designed for? Email matt_whitby@hotmail.com Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor(s): Prof. Sebastian Deterding Dr Jo Iacovides A Design Framework for Reflective Play "One of the baddies all along": Moments that Challenge a Player's Perspective “Conversations with pigeons”: Capturing Players’ Lived Experience of Perspective Challenging Games Themes Design & Development Player Research - Previous Next

< Back Connor Watts Queen Mary University of London iGGi PG Researcher I am a machine learning research engineer and software developer with commercial experience deploying and maintaining models for start-ups and larger organizations. I have experience researching and developing novel algorithms, as well as designing custom environments for application in domains such as combinatorial optimization, finance and games. Email c.watts@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor: Dr Paulo Rauber Themes Game AI - Previous Next

< Back Dr William Smith University of York Supervisor William Smith is a Reader in the Computer Vision and Pattern Recognition research group in the Department of Computer Science at the University of York. He is currently a Royal Academy of Engineering/The Leverhulme Trust Senior Research Fellow and an Associate Editor of the journal Pattern Recognition. His research interests span vision, graphics and ML. Specifically, physics-based and 3D computer vision, shape and appearance modelling and the application of statistics and machine learning to these areas. The application areas in which he most commonly works are face/body analysis and synthesis, surveying and mapping, object capture and inverse rendering. A wide variety of tools and areas of maths are often useful in his research such as: convex optimisation, nonlinear optimisation, manifold learning, learning/optimisation on manifolds, computational geometry and low level computer vision (e.g. features and correspondence). He leads a team of five PhD students and one postdoc and has published over 100 papers, many in the top conferences and journals in the field. He was General Chair for the ACM SIGGRAPH European Conference on Visual Media Production in 2019 and is Program Chair for the British Machine Vision Conference in 2020. Research themes: Game AI Game Design Computational Creativity Graphics and rendering Content creation Email william.smith@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Creative Computing Design & Development Game AI Player Research - Previous Next