Search Results

Principled and Scalable Exploration Techniques for Reinforcement Learning Theme Game AI Project proposed & supervised by Paulo Rauber To discuss whether this project could become your PhD proposal please email: p.rauber@qmul.ac.uk < Back Principled and Scalable Exploration Techniques for Reinforcement Learning Project proposal abstract: Reinforcement learning has received significant attention due to its success in training agents that play popular games such as Go , Starcraft II , Dota 2 , and others. Inefficient exploration, one of the earliest problems recognized in the field, still limits the success of reinforcement learning approaches that do not require domain knowledge. Although techniques like posterior sampling convincingly solve hard exploration problems in simple domains ( https://searchworks.stanford.edu/view/11891201 ), scalable exploration techniques remain elusive. In this project, you will develop principled and scalable exploration techniques based on reducing model uncertainty ( https://arxiv.org/abs/1609.04436 ). Besides benefiting from games as excellent testbeds, this project has the potential to radically improve automated playtesting. Supervisor: Paulo Rauber Based at:

< Back Best Game Related Research Award Goes to iGGi Today, iGGi won the Best Game Related Research Award at the Game Republic 20th Anniversary Awards!! The ceremony was part of GaMaYo #21 (by Game Makers Yorkshire and the North ) which took place today, Thursday, 23 November 2023 at Tileyard North in Wakefield, and the award was sponsored by Red Kite Games . For further details please follow this link to the related news item on Game Republic's website. Big thank yous go to the organisers, hosts and sponsor! Last but not least: a WELL DONE to the iGGi Researchers!!! Previous 23 Nov 2023 Next

< Back Intelligent Games and Game Intelligence at Develop:Brighton 12-14 July Want to improve the relationship between your game AI and your players? Or polish your VR character’s social interaction skills? Or discuss the latest academic research in the metaverse? Or just chance a flirt with Amy Smith ’s @artbhot? We are super excited to announce that @iggiphd will be attending @developconf in full force with 3 talks and over 20 researchers. This is our first big event since the pandemic and we are stoked! Who else is coming? We would love to meet you all at our stand! Click here for more information. Previous 2 Jul 2022 Next

Novel video narrative from recorded content Theme Creative Computing Project proposed & supervised by Nick Pears To discuss whether this project could become your PhD proposal please email: nick.pears@york.ac.uk < Back Novel video narrative from recorded content Project proposal abstract: In order to stimulate interest and engagement in games, it is important to give players a wide variety of video content that can provide scenario variations each time they engage with the game. However, creating a large volume of diverse video content manually is expensive and time consuming. This project aims to generate novel video narratives from recorded content with minimal human intervention. This requires automatic visual scene understanding that generates auto tagging of scene content and scene actions, either on a frame-by-frame or short clip basis. As well as understanding frame content, action segmentation strategies will be developed and evaluated. This will enable construction of short novel video narratives - for example, from a manually-defined storyline. Deep learning tools and techniques will be employed throughout this project. Supervisor: Nick Pears Based at:

< Back Children and Young People's Involvement in Designing Applied Games: Scoping Review Link Author(s) MJ Saiger, S Deterding, L Gega Abstract More info TBA Link

Training iGGi is a collaboration between Uni of York + Queen Mary Uni of London: the largest training programme worldwide for doing a PhD in digital games. Training The training programme is an essential part of the iGGi PhD. It helps students acquire the knowledge and skills they need to do great research -- research that can change both video games and wider society. The programme has a practical focus on the design and development of games. By deepening our PGRs' understanding of games, we aim to motivate and enable PhD research that has real relevance to how games are made and played. Page Index: The Modules - Bringing Researchers Together - Training Requirements The Modules Because iGGi offers a four year PhD programme, the PG Researchers (PGRs) are able to commit substantial time to this training during their first year. There are four modules, with delivery shared by the University of York and Queen Mary University of London: Game Design (York) PGRs learn how to conceive, design, prototype and playtest their own games, be it for entertainment or a 'serious' purpose like health, education, or research. Game Development (QMUL) The module provides hands-on training developing video games using industry-standard game engines. iGGi PGRs work together to prototype a new game in one week . It also introduces a range of state-of-the-art technologies for game development, such as novel interaction techniques, AI opponents and collaborators, and procedural content generation. Methods and Data (York) PGRs learn various methods for empirically studying games and players, including standard HCI methods and data science techniques for gaining insights from large game data sets. Research Impact & Engagement (QMUL) PGRs learn how to engage industry, players, and other societal stakeholders early on in their research, how to conduct responsible research and innovation that is overall beneficial to human wellbeing, and how to present their work online, to the media, and industry. Video Placeholder - to display Game Dev YouTube playlist >> For iGGi news and updates, including event announcements, follow us on social media Bringing Researchers Together A key aim of this training is to bring new researchers together as a well-connected cohort who will carry on learning from, and supporting each other throughout their studies. This has helped us build a strong iGGi community of researchers across four universities and multiple research fields, with a common goal of doing world class PhD research on games. Each module is delivered in two two-week blocks, with the exception of the remotely-supervised individual project. Six weeks of the training takes place in the Autumn of the first year, and another eight weeks is scheduled throughout the rest of first year. For researchers in receipt of an iGGi EPSRC studentship, travel and accommodation is provided for York researchers to study in London, and vice versa. Training Requirements Completing the training programme, including passing the modules, is a compulsory part of the iGGi PhD programme. The Game Development module does assume some knowledge of programming, at least the equivalent of an introductory class.

iGGi PhD Projects - listing iGGi PhD Projects 2023 Game AI This page displays the supervisor-proposed PhD projects on offer under the above stated theme: If you are interested in any of the projects listed and would like further details and/or to discuss, please email the project supervisor. Please note that you can also frame your own project independently granted that you have secured a supervisor's support. For a list of available supervisors please see the accepting students section of our website. While iGGi has checked that the project descriptions listed below are within iGGi's scope , we wish to highlight that you are still responsible for ensuring that your proposal, too, is in line with this scope, and we would further like to point out that supervisor-framed projects are not prioritised in the application selection process: they are judged by the same criteria as applicant-framed proposals. For guidance to make sure that the proposal you submit (regardless of whether it has been supervisor-framed or created entirely by you) sits within iGGi's scope please refer to this link: https://iggi.org.uk/iggi-scope Navigate to other Themes on offer: Game AI Design & Development Player Research Game Audio Game Data Immersive Technology Creative Computing E-Sports Applied Games Back to ALL Projects Game AI Automatic Evaluation of Tabletop Games This project proposal aims to research and develop methods to accurately evaluate the impact of modern Tabletop Games components in different aspects of gameplay. Price Game AI Duration Diego Pérez-Liébana Read More Game AI Principled and Scalable Exploration Techniques for Reinforcement Learning In this project, you will develop principled and scalable exploration techniques based on reducing model uncertainty. Price Game AI Duration Paulo Rauber Read More Game AI Evolving Perception for Game Agents This project will investigate game agents in open world games which evolve their senses and world representation alongside learning what actions to take in each state. We will evolve game agents with highly alien behaviours which nevertheless have high fitness in the open world environment, while investigating important scientific questions about how senses and world representations evolved in humans. Price Game AI Duration Alex Wade, Peter Cowling Read More Load More

< Back Examining the effects of video game difficulty adaptation on performance and player experience Link Author(s) M Frister, P Cairns, F McNab Abstract More info TBA Link

< Back Perceptual Distraction and its Effects on Difficulty and User Experience in Digital Games Link Author(s) M Frister Abstract More info TBA Link

< Back Delivering Bad News: VR Embodiment of Self Evaluation in Medical Communication Training Link Author(s) T Collingwoode-Williams, M Gillies, P Nambyiah, C Fertleman, X Pan Abstract More info TBA Link

< Back Approximating the Manifold Structure of Attributed Incentive Salience from Large-scale Behavioural Data: A Representation Learning Approach Based on Artificial Neural Networks Link Author(s) V Bonometti, MJ Ruiz, A Drachen, A Wade Abstract More info TBA Link

< Back Visualising Generative Spaces Using Convolutional Neural Network Embeddings Link Author(s) O Withington, L Tokarchuk Abstract More info TBA Link