Search Results

< Back Computer aided design of handwriting trajectories with the kinematic theory of rapid human movements Link Author(s) D Berio, FF Leymarie, R Plamondon Abstract More info TBA Link

< Back Speeding up genetic algorithm-based game balancing using fitness predictors Link Author(s) M Morosan, R Poli Abstract More info TBA Link

< Back The changing face of desktop video game monetisation: An exploration of exposure to loot boxes, pay to win, and cosmetic microtransactions in the most-played Steam games of … Link Author(s) D Zendle, R Meyer, N Ballou Abstract More info TBA Link

< 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 m.f.aichmueller@qmul.ac.uk Email Mastodon Other links Website https://www.linkedin.com/in/michael-aichmueller/ LinkedIn BlueSky https://github.com/maichmueller Github Supervisor(s): Prof. Simon Lucas Dr Raluca Gaina Themes Applied Games Game AI - Previous 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 A Survey on AI and Ethics: Key factors in building AI trust and awareness across European citizens. Link Author(s) Cristian Barrué, Atia Cortés, Alessandro Fabris, Francesca Foffano, Long Pham, Teresa Scantamburlo Abstract More info TBA Link

< Back Generating calligraphic trajectories with model predictive control Link Author(s) D Berio, S Calinon, FF Leymarie Abstract More info TBA Link

< Back First experiments in the automatic generation of pseudo-profound pseudo-bullshit image titles Link Author(s) S Colton, S Berns, BP Ferrer Abstract More info TBA Link

< Back Posterior Sampling for Deep Reinforcement Learning Link Author(s) R Sasso, M Conserva, P Rauber Abstract More info TBA Link

< Back George Long Queen Mary University of London iGGi PG Researcher Available for placement George is an IGGI PhD student interested in AI assisted game design, particularly in how it can be used to assist in the creation and balancing of game mechanics. After graduating with a BSc in Computer Science at the University of Essex, he joined IGGI in 2021 to be able to research how Artificial Intelligence can be applied specifically to reduce the prevalence of Min-Maxing in Role-Playing Games. A description of George's research: My research focuses on the concepts of Min-Maxing and Meta in Role-Playing Games, and how we can use AI assisted game design to reduce their prevalence. Min-Maxing in Role-Playing Game refers to the idea of building a character in a Role-Playing Game by maximising their positive traits while minimising negative ones, often through exploiting game mechanics. This can cause optimal strategies to emerge which not only have the potential to upset the game balance, but when these strategies become prominent enough in the community to form a Meta, it can have wider consequences such as the shunning of players deemed not to be using optimal strategies, and loss of creative choice when building characters. There are two methods I am looking into to reduce the effectiveness of Min-Maxing. The first is using AI to discover these Min-Maxed strategies. Secondly, how AI can be used in the game balancing process to identify and modify the mechanics which enable these strategies. Currently, I am focusing on the first method, with my research looking into how we can measure the effectiveness of units in combat scenarios to identify which units could be considered unbalanced. g.e.m.long@qmul.ac.uk Email Mastodon http://www.longhouse.dev Other links Website https://www.linkedin.com/in/georgelonghouse/ LinkedIn BlueSky Github Supervisor(s): Dr Diego Pérez-Liébana Featured Publication(s): PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games Themes Design & Development Game AI Game Data - Previous Next

< Back Examining the influence of perceptual distraction on performance in a working memory game Link Author(s) M Frister, F McNab, P Cairns Abstract More info TBA Link

< Back More than buttons on controllers: engaging social interactions in narrative VR games through social attitudes detection Link Author(s) GC Dobre, M Gillies, DC Ranyard, R Harding, X Pan Abstract More info TBA Link