Search Results

< Back Dr Cade McCall University of York Supervisor Cade McCall is an experimental psychologist. He uses games and virtual environments to study emotion, cognition, and behaviour during threatening experiences. His work explores how threat unfolds over time as revealed by dynamics in motion tracking data, psychophysiological measures, and experience-sampling. McCall is interested in supervising projects with a psychological focus, including: ● human interactions with autonomous systems ● the use of games to manipulate emotions ● social interactions within games Research themes: Games with a purpose Player experience Game analytics cade.mccall@york.ac.uk Email Mastodon https://www.york.ac.uk/psychology/staff/academicstaff/cm1582/#research-content Other links Website LinkedIn BlueSky Github Themes Applied Games Game Data Player Research - Previous Next

< Back Dr Ivan Bravi Queen Mary University of London iGGi Alum Ivan Bravi has obtained his B.Sc and M.Sc in Engineering of Computer Systems at the Politecnico di Milano, Italy. From January to July 2016 he was Visiting Scholar at the NYU’s Game Innovation Lab in New York, under the supervision of Prof. Julian Togelius. Since October 2017 he's an IGGI PhD student at Queen Mary University of London under the supervision of Simon Lucas. Ivan has published several workshop and conference papers in different venues such as IJCAI, Evostar, CIG, FDG, AAAI and CoG. Automatic playtesting of games can significantly streamline the process of designing, developing and releasing a game. It is also a possible application of Artificial General Intelligence (AGI): having a set of flexible algorithms that can play games regardless of their type decouples the two problems (playtesting and developing AGI algorithms) advancing both independently. When it comes to developing new AGI algorithms for game-playing a crucial characteristic is the ability of expressing different behaviours. Most of the research has focused on peak performance game-playing agents, this research project instead focuses on producing agents that are able to show different playing styles (behaviours) with no explicit domain information embedded in the algorithm. Behavioural expressivity arises from the parameterisable components of an algorithm. In classical Statistical Forward Planning (SFP) it is very straightforward to adjust these, e.g. how far ahead it's planning. A very important component of SFP algorithms is the heuristic function used to evaluate the quality of game states. Being able to define heuristics in a game-agnostic manner is a key element in maintaining the algorithms generally. i.bravi@qmul.ac.uk Email Mastodon Other links Website LinkedIn BlueSky https://github.com/ivanbravi Github Supervisor(s): Dr Diego Pérez-Liébana Prof. Simon Lucas Featured Publication(s): Evaluating and Enhancing Gameplay Behavioural Expressivity of Planning-Playing Artificial Intelligence for Automatic Playtesting Self-adaptive MCTS for General Video Game Playing Rinascimento: Playing Splendor-Like Games With Event-Value Functions Rinascimento: searching the behaviour space of Splendor Rinascimento: using event-value functions for playing Splendor Learning local forward models on unforgiving games Rinascimento: Optimising statistical forward planning agents for playing splendor A local approach to forward model learning: Results on the game of life game Game AI hyperparameter tuning in rinascimento Efficient evolutionary methods for game agent optimisation: Model-based is best Shallow decision-making analysis in general video game playing Evolving UCT alternatives for general video game playing Evolving game-specific UCB alternatives for general video game playing Themes Game AI Player Research - Previous Next

< Back Dr Charles Ringer University of York iGGi Alum Charlie Ringer is a researcher interested in applied Machine Learning with a focus on the ways in which we can use Deep Learning to model various facets of video games streams (e.g. stream highlights, emotional moments, in-game events, various streamer behaviours etc.). As such, his work spans many Machine Learning fields, such as Computer Vision, Affect Computing, and Natural Language Processing. His research has three motivating factors. Firstly, the challenge of how to fuse multi-view stream data (e.g. audio, web-cam footage, game footage, chat) into a single model, especially when considering the challenges of ‘in-the-wild’ data. Secondly, the untapped and bountiful data source that livestreaming represents, especially regarding the way in which streamers play games and interact with their audience. Thirdly, the exciting and emerging field of self-supervised learning which has the potential to utilise this abundance of livestream data. Charlie initially worked in the video games industry working mainly on the Magic: The Gathering - Duels of the Planeswalkers series of games before studying a BSc in Computer Science at Goldsmiths, University of London. After his BSc he joined IGGI, firstly at Goldsmiths and then at York. He was recognised as a finalist for the Twitch Research Fellowship 2019 for his research on livestream data. charles.ringer@york.ac.uk Email Mastodon https://www.charlieringer.com Other links Website https://www.linkedin.com/in/charlie-ringer/ LinkedIn BlueSky https://www.github.com/charlieringer Github Featured Publication(s): Machine Learning with Applications From Theory to Behaviour: Towards a General Model of Engagement Modelling early user-game interactions for joint estimation of survival time and churn probability Time to die 2: Improved in-game death prediction in dota 2 Autohighlight: Highlight Detection in League of Legends Esports Broadcasts via Crowd-Sourced Data Multi-Modal Livestream Highlight Detection from Audio, Visual, and Language Data Twitchchat: A dataset for exploring livestream chat Multimodal joint emotion and game context recognition in league of legends livestreams Streaming Behaviour: Livestreaming as a Paradigm for Analysis of Emotional and Social Signals Deep unsupervised multi-view detection of video game stream highlights Streaming behaviour: Live streaming as a paradigm for multi-view analysis of emotional and social signals Rolling Horizon Co-evolution in Two-player General Video Game Playing Themes Esports Game AI Game Data - Previous Next

< Back Dr Abi Evans University of York Supervisor Abi Evans is a Lecturer in Interactive Media in the Department of Theatre, Film, Television, and Interactive Media at the University of York. Her research is at the intersection of Human-Computer Interaction (HCI) and Learning Sciences, exploring how technology can provide real-time adaptive scaffolding for the skills and processes associated with effective learning in a variety of settings. Abi is particularly interested in supervising students who want to create and evaluate games and immersive experiences for learning or develop approaches for measuring learning in games. Her current project focuses on developing experiences for people who are learning to code, specifically tackling barriers to learning such as imposter syndrome and misconceptions about coding concepts. Abi would also welcome students interested in games for learning in other disciplines and in informal settings as well as traditional academic disciplines. abi.evans@york.ac.uk Email Mastodon https://www.abigailevans.org/ Other links Website https://www.linkedin.com/in/abi-evans-7294379 LinkedIn BlueSky Github Themes Design & Development Immersive Technology Player Research - Previous Next

< Back Andrew Martin Queen Mary University of London iGGi Alum 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. Programming feedback can be thought of in terms of how quickly and seamlessly the user is able to observe the results of their work. This process is usually plagued with manual tasks and long pauses. It is common that a user will need to recompile, relaunch their program, and then manually recreate whatever state is required to observe the behaviour that they are working on. Frameworks like Elm, React and Vuejs are establishing a new norm of automatic hot-reloading with state preservation. These systems represent a branch of programming language research that is strongly focused on developer experience. In order to improve upon this work for game development, we must overcome the unique challenges that game development entails. Although the systems mentioned are all quite recent, there is a rich vein of research to draw on, which can be traced through dataflow programming, Smalltalk, Erlang, functional-reactive programming, Lisp and more. Predictive completions are considered by many to be a natural next-step in the evolution of live programming environments. An AI programming assistant would propose program fragments as completions or alternatives. The agent may seek to anticipate the user’s intent, or to provide creative suggestions. There is much relevant research in the fields of program synthesis, inductive logic programming, machine learning and genetic programming. One significant problem is how to smoothly and safely integrate a system like this into the user’s workflow. Many of the properties useful for safely enabling live programming features, such as isolation of side-effects, will also permit an AI agent to safely generate and execute code. Andy graduated from Imperial College London with an MEng in Computing in 2011. Following this he worked on game engine tools and technology at a startup called Fen Research, and then as a senior developer at a software consulting firm called LShift. In 2016 he spent six months working as a Research Associate in the Computational Creativity group at Goldsmiths, before starting his PhD. Please note: Updating of profile text in progress Email Mastodon Other links Website LinkedIn BlueSky Github Themes Game AI - Previous Next

< Back Dr Nick Ballou Queen Mary University of London iGGi Alum Hi there! I’m a psychology and human-computer interaction researcher interested in two main topics: how games affect wellbeing, and how we can reform the research ecosystem to be more trustworthy and efficient (aka “open science” or “metascience”). I’m originally from the US, and have bachelor and master’s degrees in linguistics, a topic that prepared me well for social science research, but whose use is relegated to excitedly sharing language fun facts at this point. In my free time, I play tennis, cook and bake, read—and of course play games (mostly deckbuilders, roguelikes, and AAA RPGs). A description of Nick's research: Psychological need frustration—experiences of feeling controlled and coerced, failure and self-doubt, or loneliness and exclusion—is a promising framework for understanding how players engage with video games. Grounded in self-determination theory, one of the most robust psychological theories, need frustration might help explain how and why players (dis)engage with a game and how gameplay impacts well-being. To realize this aim, however, we’re missing key building blocks: 1) a better grasp on when and why need-frustrating situations arise during play; 2) a questionnaire that can assess how much need frustration people experience in games quantitatively; and 3) studies that combine data on need frustration with carefully tracked behavioral data over time, rather than relying on simple self-reports like “how much time did you spend playing video games last week?” My thesis attempts to address all of these one step at a time and is underpinned by a strong emphasis on open and transparent methods. Results so far are promising—contact me to hear more! nick@nickballou.com Email Mastodon https://www.nickballou.com Other links Website LinkedIn BlueSky Github Supervisors: Prof. Sebastian Deterding Dr David Zendle Dr Laurissa Tokarchuk Featured Publication(s): Reliving 10 years old: Descriptive Insights into Retro Gaming UKRN Local Network Lead Guidebook Claims for no evidence also need evidence From social media to artificial intelligence: improving research on digital harms in youth The Basic Needs in Games (BANG) Model of Video Game Play and Mental Health (PhD thesis) The Basic Needs in Games (BANG) Model of Video Games and Mental Health: Untangling the Positive and Negative Effects of Games with Better Science The Relationship Between Lockdowns and Video Game Playtime: Multilevel Time-Series Analysis Using Massive-Scale Data Telemetry Affective Uplift During Video Game Play: A Naturalistic Case Study No evidence that Chinese playtime mandates reduced heavy gaming in one segment of the video games industry A manifesto for more productive psychological games research Four grand challenges for video game effects scholars: How digital trace data can improve the way we study games Perceived value of video games, but not hours played, predicts mental well-being in adult Nintendo players Development of the Brief Open Research Survey (BORS) to measure awareness and uptake of Open Research practices The Basic Needs in Games Scale (BANGS): A new tool for investigating positive and negative video game experiences How does Juicy Game Feedback Motivate? Testing Curiosity, Competence, and Effectance Registered Report Evidence Suggests No Relationship Between Objectively Tracked Video Game Playtime and Well-Being Over 3 Months How do video games affect mental health? A narrative review of 13 proposed mechanisms Learnings from the case Maple Refugee: A dystopian story of free-to-play, probability, and gamer consumer activism. Four dilemmas for video game effects scholars: How digital trace data can improve the way we study games Cross-cultural patterns in mobile playtime: an analysis of 118 billion hours of human data Pinpointing the problem: Providing page numbers for citations as a crucial part of open science A large-scale study of changes to the quantity, quality, and distribution of video game play during the COVID-19 pandemic Reforms to improve reproducibility and quality must be coordinated across the research ecosystem: the view from the UKRN Local Network Leads ‘I Just Wanted to Get it Over and Done With’: A Grounded Theory of Psychological Need Frustration in Video Games A Manifesto for More Productive Psychological Games Research Understanding whether lockdowns lead to increases in the heaviness of gaming using massive-scale data telemetry: An analysis of 251 billion hours of playtime If everything is a loot box, nothing is: Response to Xiao et al. Awareness of and engagement with Open Research behaviours: Development of the Brief Open Research Survey (BORS) with the UK Reproducibility Network Do People Use Games to Compensate for Psychological Needs During Crises? A Mixed-Methods Study of Gaming During COVID-19 Lockdowns Self-Determination Theory in HCI: Shaping a Research Agenda Themes Game Data Player Research Previous Next

< Back Filip Sroka Queen Mary University of London iGGi PG Researcher Filip is a Computer Science researcher specialising in Game AI. He acquired an Integrated Masters in Computer Science from Queen Mary University of London and is pursuing a PhD in Game AI with iGGi. With a passion for algorithms and problem-solving, he constantly seeks new challenges to enhance his skills. As an avid LEGO collector and investor, he brings a unique blend of technical and creative abilities. He is excited about the potential of the Metaverse and is driven by the role of technology in shaping its future. His research explores the integration of Dynamic Difficulty Adjustment (DDA) into VR rhythm games such as Beat Saber, with the goal of enhancing player skill development and motivation through the application of learning theories. By addressing difficulty spikes, the project creates personalised learning experiences using human-made maps designed to accelerate the learning process. Key components include player evaluation, map segmentation, and procedural generation. The broader aim is to extend these findings to other rhythm games, offering benefits to players, game developers, and the health and fitness industry. f.sroka@qmul.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/filip-sroka-134954197/ LinkedIn BlueSky https://github.com/FilipSroka Github Supervisor: Dr Laurissa Tokarchuk Themes Applied Games Game AI Immersive Technology - Previous Next

< Back Dr Agnieszka Lyons Queen Mary University of London Supervisor Agnieszka Lyons is a linguist and discourse analyst specialising in digitally mediated communication and multimodal communication, particularly across geographic distance. She explores the ways in which users of digital media construct their digitally mediated personae, particularly from the perspective of performance of the embodied selves, entering intersubjective spaces through verbal and non-verbal discourse and creating the feeling of physical and social presence across geographical distance. This can include multimedia sharing, avatar design, textual representation of nonverbal content, and others. She is particularly interested in supervising students with a communication, HCI, social and behavioural sciences background on the following topics: Player experience Player in-game interaction Construction of alternative personae Performance of player identities a.lyons@qmul.ac.uk Email Mastodon https://agnieszkalyons.wordpress.com/ Other links Website https://www.linkedin.com/in/agnieszka-lyons-3831592/ LinkedIn BlueSky Github Themes Player Research - Previous Next

< Back Dr Zoe Handley University of York Supervisor Zoe Handley is a Senior Lecturer (Associate Professor) in Language Education. She is an interdisciplinary researcher, with a background in language technology, who recognizes the value of quantitative as well as qualitative work in this area. Her earlier work focused on the evaluation of speech synthesis for use in language learning and teaching. Since then she has carried out a systematic review of evidence for the use of technology to support English language learning in primary and secondary schools and supervised a number of theses evaluating applications of technology for language learning. These have typically explored the use of web 2.0 and Computer-Mediated Communication (CMC) technologies. Further to this she is interested in how learners autonomously use technology to support their learning in contexts such as study abroad. Zoe is currently particularly interested in teacher thinking in relation to the integration of technology to support language learning and developing and evaluating training to support teachers in making decisions about what technologies to integrate into their teaching, for what purposes and how. Zoe welcomes applications from PhD students interested in designing and evaluating educational activities that harness the affordances of digital technologies to create conditions and engage learners in processes that are known to support language learning. zoe.handley@york.ac.uk Email https://sites.google.com/york.ac.uk/pivotal-group/about Mastodon https://www.york.ac.uk/education/our-staff/academic/zhandley/ Other links Website https://www.linkedin.com/in/zoe-handley-a730b58/ LinkedIn BlueSky Github Themes - Previous Next

< Back Dr Yizhao Jin Queen Mary University of London iGGi Alum Currently a student at Queen Mary University of London (QMUL), I have delved deep into the realms of artificial intelligence and game design. With a passion for understanding the complexities behind real-time strategy (RTS) games and their dynamic, unpredictable nature, I have committed myself to contribute novel insights to this domain. Research: My primary research area is Hierarchical Reinforcement Learning (HRL) for Real-Time Strategy (RTS) games. RTS games, known for their intricate mechanics and vast decision spaces, present a formidable challenge for traditional AI approaches. By employing HRL, I aim to develop agents that can not only understand the multi-layered tactics and strategies of these games but also learn to adapt to ever-changing game scenarios efficiently. The main objectives of my research are: Better Generalization: To create agents that can seamlessly transition between different RTS games or various maps within the same game without extensive retraining. This involves understanding common strategic threads across multiple game domains. Efficient Training: RTS games are inherently time-consuming due to their vast decision spaces and prolonged gameplay. My research seeks ways to optimize the training process, ensuring that AI agents can learn faster and with fewer computational resources. acw596@qmul.ac.uk Email Mastodon Other links Website LinkedIn BlueSky https://github.com/decatt Github Supervisors: Prof. Greg Slabaugh Prof. Simon Lucas Themes Game AI Previous Next

< Back Igor Dall'Avanzi Goldsmiths iGGi Alum Creation of accessible tools for the use of procedural audio in video games The aim of this research is to investigate and provide new tools to developers for the use of procedural audio into video games. Procedural approaches could address different issues that commonly afflict game audio. In music, generative systems are not only less repetitive, but offer more adaptability as well. For what concerns sound design, they can provide not only variety, but stronger and more realistic support to the interaction with the game world; interaction that is becoming even deeper with the advent of VR Yet, these methods still need improvement on different sides. One is the level of quality that procedural audio needs to achieve to compete with the current aesthetic established by the use of rendered sounds and music in the media. Another is the additional amount of work required by the CPU to render the assets on runtime, and its variable cost). Finally, there is a general lack of user-friendly tools, to link common programming languages for audio to game engines. Software like MaxMsp, Pure Data or SuperCollider is used to design generative audio systems. A more accessible integration of these software could promote generative approaches among sound designers and composers in the field, that today have instead access to tools mainly designed to be used with rendered assets. My plan is to bring on research first by focusing on how a higher degree of quality could be addressed, exploring tools like the above mentioned MaxMsp, Pure Data, low level solutions, and machine learning algorithms. Primary research will be run to confront procedurally generated audio content with rendered one; to understand its impact on the player, and the level of quality needed to deliver a satisfactory experience. The creation of more accessible interfaces and tools dedicated to implement procedural audio in video games will be investigated and undertaken. I like to make noises of all sort and to play with them. For this reason I graduated in Music Production in 2016 and, at the moment of writing, I am finishing my final project for an MSc in Sound and Music for Interactive Games at Leeds Beckett University. Composer and sound designer, in the last year I have been focusing on audio implementation and programming, and I am currently exploring machine learning approaches for procedural audio. Please note: Updating of profile text in progress Email Mastodon Other links Website LinkedIn BlueSky Github Themes Game Audio Player Research - Previous Next

< Back Peyman Hosseini Queen Mary University of London iGGi PG Researcher Peyman is interested in using his computer science knowledge to support society's well-being. Raised in a family where almost everyone’s work is somehow related to mathematics and its applications, he became passionate about algorithms and combinatorics from an early age. This prompted him to pursue an undergraduate degree in computer engineering with a focus on IT and AI. This background led him to start his PhD at IGGI on building more powerful yet efficient Natural Language Processing models for analysing textual data, a rich and abundant source of gaming feedback. A description of Peyman's research: Peyman's research focuses on advancing deep learning architectures for natural language processing and building tools on top of state-of-the-art models. To contribute to the fundamental understanding and practical application of deep learning in natural language processing, focusing on efficiency and effectiveness, he pursues two main objectives: Designing more efficient models that match or surpass state-of-the-art performance with fewer parameters. Systematically analyzing language models to develop solutions that enhance their effectiveness for end-users, such as game studios. His recent accomplishments towards these goals include: 1. Developing novel attention mechanisms: 1.1 Optimized Attention: 25% parameter reduction 1.2 Efficient Attention: 50% parameter reduction 1.3 Super Attention: 25% parameter reduction with significant performance improvements in language and vision tasks 1.4 All mechanisms demonstrate comparable or superior performance to standard attention across various inputs. 2. Designing and training Hummingbird , a proof-of-concept small language model using Efficient Attention, available on HuggingFace. 3. Conducting a study on large language models' limitations in analyzing lengthy reviews for basic NLP tasks. Proposed solutions offer substantial performance improvements while reducing API costs by more than 90%. s.hosseini@qmul.ac.uk Email Mastodon https://peymanhosseini.net/ Other links Website https://www.linkedin.com/in/peyman-hosseini1 LinkedIn BlueSky https://github.com/Speymanhs Github Supervisors: Dr Ignacio Castro Prof. Matthew Purver Featured Publication(s): 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