Output details
11 - Computer Science and Informatics
University of York
Information Set Monte Carlo Tree Search
<22>Extends Monte Carlo Tree Search to domains with information asymmetry (e.g. card games, board games, security applications). Techniques implemented in a commercial mobile phone game (AI Factory's Spades - see collaborative AAAI-AIIDE 2013 paper, "Integrating Monte Carlo Tree Search with knowledge-based methods to create engaging play in a commercial mobile game") with over 2.5m downloads, greatly increasing playability and strength, with excellent customer reviews. Influenced recent work on integration with big data approaches in subsequent £1.2m NEMOG EPSRC project (York/Cass/Durham) collaborating with AI Factory. Well received at RAEng soiree, 8 schools, 2 invited tutorials, 20+ conferences/meetings, taught MSc courses.