Search Results

< Back Prof. William Latham Goldsmiths iGGi Co-Investigator Supervisor William Latham is well known for his pioneering organic computer art created in the 80s and early 90s whilst a Research Fellow at IBM in Winchester. In 1993 he moved into Rave Music setting up a small studio in Soho, creating album covers, stage designs and videos for bands including The Shamen for three years. He then worked for ten years as Creative Director and CEO of a large computer games development company, with studios in London and Brighton, creating PC and console games published by Vivendi Universal, SONY and Warner Bros. Among the games he has produced were Evolva for Virgin Interactive, and the hit game The Thing for Vivendi Universal for Xbox, PlayStation, PC. based on the famous John Carpenter horror movie set in Antarctica. In 2007, he became a Professor in Computing at Goldsmiths, where he works on research projects with Imperial College, York University, and the Oxford Weatherall Institute. His recent "Mutator VR" Sci-Fi art experience developed at Goldsmiths for the HTC Vive has been exhibited to much acclaim in galleries and museums Shanghai, Venice, Kyoto, Dusseldorf and St. Petersburg. William was an undergraduate student at Christchurch College, Oxford University, and a postgraduate student at The Royal College of Art. His book on interactive evolutionary design, “Evolutionary Art and Computers” is cited as a leading publication in this domain. He is Director of SoftV Ltd, a company which develops Neuroscience Patient mobile Games Apps for the NHS in Unity, and is a co-founder of London Geometry Ltd. Email w.latham@gold.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Creative Computing Immersive Technology - Previous Next

< Back Michael Aichmüller Queen Mary University of London iGGi Alum My background lies in physics and statistical mathematics with a later specialization in optimization in the fields of Reinforcement Learning (RL) and Causal Inference. My first encounters with RL occurred during my Masters when studying how to create strong policies in perfect information games using algorithms, such as MinMax, MCTS, DQN, and later AlphaZero variants. My favorite game application remains the board game ‘Stratego’. In the meantime I investigated the estimation of causal parents influencing a target variable from interventional datasets for my Master’s thesis. Specifically, how well Deep Learning estimations could replace exponentially scaling graph search methods with approximations requiring only polynomial runtime. A description of Michael's research: My research focuses on the state-of-the-art in game-playing solutions for imperfect information games (think games like Poker, Stratego, Liar’s Dice etc.). I am particularly interested in the application of No-Regret (and related) methods which seek to learn those actions that provided the most benefit (or least regret) compared to the benefit all possible actions provided on average. These methods learn such via iterative play to find a Nash-Equilibrium (NE), a game-theoretic concept comparable to an optimal policy known from Single-Agent RL, but for all partaking players at once. Particularly, variants of Counterfactual Regret Minimization (CFR) remain the state-of-the-art algorithms for computing NEs in 2-player zero-sum games due to their success in tabular form so far. Yet, prohibitive complexity and memory scaling bars them from large-scale applications. Hence, research of recent years seeks to couple CFR (and other No-Regret methods) with function approximation, such as Deep Learning, to scale up the size of applicable games with already notable successes (Deepstack, Libratus, Pluribus, DeepNash). My research seeks to contribute to this endeavour by first analyzing the specifics of established methods and finding ways to introduce Hierarchical RL concepts to No-Regret learning. Please note: Updating of profile text in progress Email m.f.aichmueller@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor(s): Prof. Simon Lucas Dr Raluca Gaina Themes Applied Games Game AI - Previous Next

< Back Prof. Anders Drachen Supervisor Anders Drachen, PhD, (born 1976) is a Professor at the Department of Computer Science, with Digital Creativity Labs and Weavr at the University of York (UK). His work in games research is focused on user behavior, user experience and audience engagement and the application of data science, information systems modelling, business intelligence, design and Human-Computer Interaction in these domains. His research and professional work are carried out in collaboration with companies across the Creative Industries, from big publishers to indies. He is recognized as one of the most influential people in his domains of work and have authored over a hundred publications with international colleagues across industry and academia. Having lived and worked on four different continents, Anders Drachen has had the mixed pleasure of fending off three shark attacks in Africa and Australia. He is also the youngest Dane in history to publish a cooking book – dedicated to ice cream. Research themes: Data Science, Analytics, Machine Learning in Interactive Media Big Data, behavior- and social media analytics in the Creative Industries Data Mining and Business Informatics in the Creative Industries Data-Driven Storytelling and Audience Engagement Games User Research and User Experience in Games Data-Driven Design and Development Human-Computer Interaction Esports and Sports Analytics Behavioral/Market Analytics and Business Intelligence Entrepreneurship in the Creative Industries Blockchain and Cryptocurrencies Email anders.drachen@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Design & Development Esports Game Data Player Research - Previous Next

< Back Dr Marko Tot Queen Mary University of London iGGi Alum Hello! I'm Marko, and welcome to my page! As a part of the IGGI programme and Game AI research group, I'm working on adapting Statistical Forward Planning methods for complex environments. Statistical Forward Planning methods have proven to be effective in some simpler domains and, without requiring any prior learning, they provide a good out of the box AI algorithm. However, while these algorithms shine in certain games, they struggle to perform well in cases where the reward received from the game is sparse. In games where it takes a series of optimal actions to reach the goal, without any significant feedback from the environment in between, their performance drops significantly. My research is centered on solving this problem through automatic sub-goal generation and utilisation of local learned forward models. Creation of the sub-goals could be used to simulate the feedback from the environment and give regular rewards to the agent even in sparse and complex environments. I started my journey in video games when I got my first PC at the age of six, and at that point it was decided that I'm going to make a career out of it. So here I am, ~20 years later, a PhD. student at Queen Mary University of London, trying to make AI agents that can play games, and regularly spending too much time playing games under the excuse that it's all for 'research purpose'. Email m.tot@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor(s): Dr Diego Pérez-Liébana Featured Publication(s): Adapting a world model for trajectory following in a 3d game Bootstrap Your Own Teacher: Online Policy Distillation for Multi-Game Reinforcement Learning Statistical Forward Planning Algorithms World and human action models towards gameplay ideation Turning Zeroes into Non-Zeroes: Sample Efficient Exploration with Monte Carlo Graph Search Making Something Out of Nothing: Monte Carlo Graph Search in Sparse Reward Environments What are you looking at? Team fight prediction through player camera Themes Game AI - Previous Next

< Back Peyman Hosseini Queen Mary University of London iGGi PG Researcher Peyman Hosseini is a PhD candidate working on Agentic AI and building on efficient solutions with small language models and post-training of large and small language models to enable these LLMs to be powerful on-device assistants. He has interned for the last 12 months at Samsung Research in the UK where he has led 3 paper sumbissions and 2 patent submissions on post training foundation models with reinforcement learning algorithms as well as building efficient on-device memory agents. A description of Peyman's research: Peyman's Rsearch targets post-training of foundation models, specifically large language models, to deliver personalized and powerful AI-powered solutions that are deployable on edge devices, such as mobile phones and personal computers. This is specifically important as Large Language Models (LLMs) are powerful yet impossible to deploy on edge-devices to their computational requirements. On the other hand, Small Language Models (SLMs), i.e., language models between 2-32B params, are more efficient but yet unable to handle complex tasks. Fine-tuning these models to work well in complicated setting enables a lot powerful, privacy-preserving AI-powered applicatios, such as personalized on-device recommendation systems and agents capable of memorizing users' habits and interests. Email s.hosseini@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr Ignacio Castro Prof. Matthew Purver Featured Publication(s): CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models Cost-Effective Attention Mechanisms for Low Resource Settings: Necessity & Sufficiency of Linear Transformations Efficient solutions for an intriguing failure of llms: Long context window does not mean LLMs can analyze long sequences flawlessly Brain Drain Optimization (BRADO) Algorithm to Solve Multi-Objective Expert Team Formation Problem in Social Networks You Need to Pay Better Attention: Rethinking the Mathematics of Attention Mechanism GeoPos: A Minimal Positional Encoding for Enhanced Fine-Grained Details in Image Synthesis Using Convolutional Neural Networks Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction GRACER: Improving the Accuracy of RACER Classifier Using A Greedy Approach Themes Game AI Player Research - Previous Next

< Back Dr Joseph Walton-Rivers University of Essex iGGi Alum Controlling Non-player characters. (Industry placement at Visteon) Within games non-player characters help to sell the world and give meaning to the player's experiences. These characters in games are presently not very believable and often lack the ability to interact with each other in meaningful ways. This work is looking at creating socially capable, believable agents to populate the worlds of role playing games. These agents need to be able to cope with player's actions and be capable of acting independent in the world. Joseph studied computer science at the University of Essex, obtaining a first class degree. During his study there he received two awards for academic achievement. After graduation he worked in the IT team of a company with offices across the United Kingdom where he developed and maintained their IT systems. Since starting IGGI he has worked on research involving co-operative agents working together to solve shared goals. He has a keen interest in programming and the Free Software movement. During his free time he enjoys strategy and puzzle games including Prison Architect, the Shadowrun series and Galactic Civilization 2. Please note: Updating of profile text in progress Email Website LinkedIn Mastodon BlueSky GitHub Other Link Featured Publication(s): Peer Evaluation in Group Projects: Insight into Effective Student Critique and Feedback Evaluating the Effects on Monte Carlo Tree Search of Predicting Co-operative Agent Behaviour An Exploratory Analysis of Student Experiences with Peer Evaluation in Group Game Development Projects Student Perspectives on the Purpose of Peer Evaluation During Group Game Development Projects The 2018 Hanabi competition Hexboard: A generic game framework for turn-based strategy games Fireworks agent competition Evaluating and Modelling Hanabi-Playing Agents Controlling co-incidental non-player characters Monte carlo tree search applied to co-operative problems Distributed Social Multi-Agent Negotiation Framework For Incomplete Information Games Themes Player Research - Previous Next

< Back Dr Ben Kirman University of York iGGi Training Coordinator Supervisor Available to supervise non-iGGi students for 2024 intake Ben is a Senior Lecturer (Associate Prof) in Interactive Media at the University of York, who has over 20 years' experience as a creative technologist. Since his first programming job fixing Y2K bugs (you're welcome), he has worked with dozens of organisations, large and small, in design and prototyping playful experiences. His research uses game design and playful design as a way to explore the complex effects of emerging technologies through novel and unexpected interactions and experiences. Most often, this is through the design and development of games, digital/physical prototypes, and design fictions. Ben has applied this in topics ranging from immersive theatre, dog technology, non-league football, radical cycle delivery, and time travelling robots, to educational games, esports, new situationism and magic. The unifying theme is play – as a topic of study, a way of working, for research insight, and as expression or output in games or playful experiences. This work, especially the more bizarre stuff, has often been covered by traditional media, including the BBC, New Scientist, Wired, The Guardian, TIME, Metro, the New York Times, and Your Cat magazine. Ben is keen on supervising students with strong creative drives, with an interest in making, design, experimentation, and a broad perspective on games and play. This might be a project about playful props in immersive theatre, or a project about context in locative and site-specific games, or any other project that looks to explore new possibilities and new implications of emerging technology through the lens of play. Research themes include: Game Design Applied Games Computational Creativity Sports with an E and without an E Player Experience Email ben.kirman@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Applied Games Creative Computing Design & Development Esports Player Research - Previous Next

< Back Dr Lorenzo Jamone Queen Mary University of London Supervisor I am a Lecturer in Robotics and Director of the CRISP group (Cognitive Robotics and Intelligent Systems for the People) at the School of Electronic Engineering and Computer Science (EECS) of the Queen Mary University of London (QMUL). The CRISP group is part of ARQ (Advanced Robotics at Queen Mary). Since October 2018, I have been a Turing Fellow at The Alan Turing Institute. I am interested in understanding human (and animal) intelligence, by using computational techniques that include computer simulations and real robots. My research topics include: human creativity and creative problem solving, human perception, human-human non-verbal communication, object affordances, tool use, body schema, eye-hand coordination, dexterous manipulation and object exploration, human-robot interaction and collaboration, tactile and force sensing. I am interested in supervising students with an engineering, computer science or behavioural sciences background on the following topics: Creating computational models of human creativity Creating computational models of decisional agents Email l.jamone@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Applied Games Creative Computing - Previous Next

< Back Dr Alan Pedrassoli Chitayat University of York iGGi Alum Available for post-PhD position Alan is a researcher that focuses on audience experience within esport broadcast. His Machine Learning background allows him to extract complex patterns from game and game related data in order to derive meaningful insights that can be utilised in broadcast. Having worked in the esport industry, both as a software engineer as well as researcher, Alan has experience with both technical and research problems. His research aims to explore the factors that improve the audience experience within esports. This is catered to esport broadcast of all levels, from highly produced professional tournaments to regular streams by content creators and it could be in the form of: Measuring and representing different forms of audience engagement. Exploring the different ways to visualise and utilise Machine Learning to enhance and integrate existing broadcast pipelines. Investigating how community-led narratives can be generated through data. Email alan.pchitayat@york.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisors: Dr James Walker Prof. Anders Drachen Featured Publication(s): AI vs. the Algorithm: Measuring success on Twitch Applying machine learning to enhance esport broadcast narratives Beyond the Spotlight: Co-Designing AI for Theatre Audience Communication How Could They Win? An Exploration of Win Condition for Esports Narratives Applying and Visualising Complex Models in Esport Broadcast Coverage From Passive Viewer to Active Fan: Towards the Design and Large-Scale Evaluation of Interactive Audience Experiences in Esports and Beyond Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analitics Data-Driven Audience Experiences in Esports Metagaming and metagames in Esports What are you looking at? Team fight prediction through player camera Echo Suite of Software (Showcase Brochure) Automatic Generation of Text for Match Recaps using Esport Caster Commentaries WARDS: Modelling the Worth of Vision in MOBA's DAX: Data-Driven Audience Experiences in Esports Themes Design & Development Esports Game Data - Previous Next

< Back Zoë O’Shea Goldsmiths iGGi PG Researcher Zoë O’Shea is an Irish freelance games designer and artist, working on her thesis in game design and player psychology. Her previous qualifications include 3D Generalism, and an MA in Digital Game Design and Theory. She is endlessly curious about the meaning and value that technology can bring to the world, exploring the human experience as a core principle of her work. She firmly believes in the importance of creating a more joyful and inclusive world. Zoë has previously worked with a range of clients and companies including A Brave Plan, Surgent Studios, Transport for London (TfL) and LEGO. In 2019, Zoë was awarded a Digital Fellowship from the Royal Shakespeare Company (RSC) in collaboration with Magic Leap. Zoë worked with other creatives for a year to explore the future of theatre and Spatial Computing (Mixed Reality). The programme completed in Feb 2020, through the generous support of Magic Leap, the RSC, their technologists, industry partners, i2 Media Research and the University of Portsmouth. Currently, Zoë is working on completing her thesis while offering consultancy services for games and start-ups looking to expand their knowledge in soft aesthetics, tend & befriend game design and immersive technology. A description of Zoë's research: Tend & Befriend: A New Perspective on Player Psychology in Digital Games Many are familiar with the term "fight-or-flight" - a stress response activated when animals come into conflict with a stressor or threat. Less commonly known is "tend & befriend", an alternative theory of stress response which suggests that engaging with tending and affiliative behaviours under duress can soothe and protect us. This thesis investigates this phenomenon in digital games, with a focus on empirical data and design. Results demonstrate a consistent niche in the games industry for "tend & befriend" centric design and the value in synthesising previous design frameworks to create a intentional and polished experience for players. Email z.oshea@gold.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Supervisor(s): Prof. Richard Bartle Featured Publication(s): The impact of self-representation and consistency in collaborative virtual environments Themes Design & Development Immersive Technology Player Research - Previous Next

< Back Dr Miles Hansard Queen Mary University of London Supervisor Miles Hansard is a computer vision researcher, working on geometric and statistical methods for 3D scene understanding and rendering. He is also interested in active 3D sensing technologies, including depth cameras, lidar, and millimetre-wave radar. His recent projects include GPU methods for real-time atmospheric effects, commodity radar localization of UAVs, and grasp planning for robotic manipulation. He has also worked on human perceptual processes, including eye-movements, geometric judgements, and binocular stereopsis. Miles Hansard is a Senior Lecturer in computer graphics, and a member of the Vision Group and Centre for Advanced Robotics, at QMUL. He is available to supervise projects in the following areas: Simulation of complex physical effects (e.g. the motion of cloth, fire, and fluids), using machine learning. Physically plausible character animation in complex environments (e.g. slippery terrain), using machine learning. Email miles.hansard@qmul.ac.uk Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Design & Development Game AI Game Data Immersive Technology - Previous Next

< Back Dr Thryn Henderson University of York iGGi Alum Thryn’s phd explored the practices of personal vignette games, with a particular interest in the vignette game’s approaches to digital persona, their roots in approachable DIY culture, and their importance to marginalised creators. Publications from their work can be found in the Digra 2020 archive and Persona Studies Volume 6, Issue 2 . Thryn’s interest in gaming grows from a delight in telling stories. They endeavour to find the spaces where play incorporates and encourages collaborative narrative, poetry, theatre, activism, subversion, surprise and expression. Most of Thryn’s work in playful media can be found in zines, cardboard installations, paper games, hidden screens, or roaming through the woods around the UK. They are a co-founder of the playful design co-operative Furtive Shambles, currently producing experimental live and tabletop game experiences. Email thrynhenderson@gmail.com Website LinkedIn Mastodon BlueSky GitHub Other Link Themes Design & Development - Previous Next