Search Results

< Back Navigating the Lines: Towards a Multi-Perspective Approach on Videogame Monetisation Link ​ Author(s) P Declerck, B Dupont, E Grosemans, E Petrovskaya, M Geudens, M Sas, ... Abstract ​ More info TBA ​ Link

< Back Design and implementation of TAG: a tabletop games framework Link ​ Author(s) RD Gaina, M Balla, A Dockhorn, R Montoliu, D Perez-Liebana Abstract ​ More info TBA ​ Link

< Back How Players Learn Team-versus-Team Esports: First Results from A Grounded Theory Study Link ​ Author(s) J Hesketh, CS Deterding, J Gow Abstract ​ More info TBA ​ Link

< Back IoT and Machine Learning for Next Generation Traffic Systems Link ​ Author(s) S Howell, S Cole, T Broad, T Maatta Abstract ​ More info TBA ​ Link

< Back The Effects of a Soundtrack on Board Game Player Experience Link ​ Author(s) T Farkas, A Denisova, S Wiseman, R Fiebrink Abstract ​ More info TBA ​ Link

< Back DAX: Data-Driven Audience Experiences in Esports Link ​ Author(s) A Kokkinakis, SP Demediuk, I Nölle, O Olarewaju, S Patra, J Robertson, P York, AP Chitayat, A Coates, D Slawson, P Hughes, N Hardie, B Kirman, JD Hook, A Drachen, M Ursu, FO Block 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 Twitter https://github.com/maichmueller Github Supervisor(s): Prof. Simon Lucas Dr Raluca Gaina ​ Themes Applied Games Game AI - Previous Next

< Back Crowdsourcing and aggregating nested markable annotations Link ​ Author(s) C Madge, J Yu, J Chamberlain, U Kruschwitz, S Paun, M Poesio Abstract ​ More info TBA ​ Link

< Back Win or learn fast proximal policy optimisation Link ​ Author(s) DS Ratcliffe, K Hofmann, S Devlin Abstract ​ More info TBA ​ Link

< Back Extracting learning curves from puzzle games Link ​ Author(s) R Volkovas, M Fairbank, JR Woodward, S Lucas Abstract ​ More info TBA ​ Link

< Back ​ Dr Shanxin Yuan Queen Mary University of London ​ Supervisor ​ ​ Dr Shanxin Yuan is a Lecturer in Digital Environment at Queen Mary University of London. He has rich expertise in deep learning, low level computer vision, and 3D digital modelling of humans from photographs. His PhD thesis focused on 3D hand pose estimation, his work is well recognized in the academia and is also deployed into commercially launched mass market mobile phones. His current research on digital humans focuses reconstructing, modelling, and rendering digital twins. He is interested in super-realistic immersive gaming, body/hand pose and facial expression retargeting, and behaviour analysis with avatars. For the new project in 2023, we are interested in working on human facial expression estimation, high-res realistic face reconstruction and rendering, face re-enactment, and face augmentation. The aim of the project is to build an editable super-realistic 3D human face model that can express novel expressions, views, shapes, and appearance, from multiple sources of input, such as images, sounds, and key points. The related techniques include deep learning, computer vision, natural language processing, and neural rendering. ​ shanxin.yuan@qmul.ac.uk Email Mastodon https://shanxinyuan.github.io/ Other links Website https://www.linkedin.com/in/shanxin-yuan-4859b656/ LinkedIn Twitter Github ​ ​ Themes Applied Games Creative Computing Game AI Immersive Technology Player Research - Previous Next

< Back Testing game mechanics in games with a purpose for NLP applications Link ​ Author(s) C Madge, J Chamberlain, R Bartle, U Kruschwitz, M Poesio Abstract ​ More info TBA ​ Link