UCT for Games and Beyond

Lead Research Organisation: University of York
Department Name: Computer Science

Abstract

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.

Publications

10 25 50

Related Projects

Project Reference Relationship Related To Start End Award Value
EP/H049061/1 01/10/2010 31/08/2012 £397,316
EP/H049061/2 Transfer EP/H049061/1 01/09/2012 28/02/2014 £166,170
 
Description We developed and refined Information Set Monte Carlo Tree Search - a sophisticated algorithm to search possible game futures in order to make good decisions in games and problems which can be modelled as games. The importance of this finding is underlined by the feedback from the external examiner for the PhD student associated with this award, Dr David Silver of Google Deepmind, reported in the Guardian as the "intellectual powerhouse" behind Google's 2016 AlphaGo triumph (https://deepmind.com/research/alphago/). We greatly extended the range of decisions that can be modelled to consider situations where there is hidden information (e.g. one player cannot see another's hidden cards/assets/disposition) which has the potential to allow many real-world decisions to be modelled as well. We published 15 papers, including a survey cited 687 times to date (Google Scholar 15th March 2017 - see http://ieeexplore.ieee.org/document/6145622/), an extended article in the top AI journal "Artificial Intelligence" and 5 papers in the top IEEE Transactions on Computational Intelligence and AI in Games. We have several keynote talks and tutorials at industry and academic conferences (see narrative impact), had our technology included in a commercial game downloaded over 5 million times, and influenced design decisions at AI Factory Ltd., Creative Assembly and Microsoft Games (see narrative impact).

Our research allowed us access to a wealth of commercial gameplay data. Mining the data from the way that human opponents have played against our AI has provided a new avenue for research into human behaviour and a new way to provide strong and more entertaining players for AI Factory - resulting in high-level journal papers and presentations at leading games industry conferences. A relationship with top games developer Electronic Arts, as well as with Microsoft Research (leading to a funded PhD student), has subsequently been built on these foundations.

The NEMOG, IGGI and DC Labs grants also reported on ResearchFish, and several smaller funded projects, are all built on the foundations of this research grant - particularly the partner relationships in the games industry. For example the IGGI Centre for Doctoral Training had the same university partners as this grant, together with several industry partners with whom we have built strong links.

NOTE: from 2018 submission the research and impacts from this project have been picked up by Digital Creativity Labs (EP/M023265/1) Creative Media Labs (AH/S002839/1) and the IGGI Centre for Doctoral Training (EP/L015846/1 and EP/S022325/1) - so further developments will be reported through this route.
Exploitation Route The URL is http://mcts.ai/ (this is temporarily down due to a lapse of project funding - though we aim to bring it back up again).

Games companies - new methods for decision making in digital games (e.g. AI Factory Ltd and Creative Assembly above - with interest from Lionhead (Microsoft), Team17 and Moon Collider - and secondments currently under discussion for PhD students on the IGGI Centre for Doctoral Training).

Games companies - modelling human players and creating AI bots which emulate human play - and hence provide more fun, engaging and profitable games.

Other decisions modelled as game theoretic models with competing/collaborating agents (e.g. in game theoretic financial models or cooperative/competitive resource allocation problems) in a wide range of industries.

We have spearheaded research into Monte Carlo Tree Search (MCTS) since its invention in 2006. Google have used related MCTS techniques in the recent high-profile triumph by Google Deepmind against human Go champion Lee Seedol. Carnegie Mellon and University of Alberta have recenlty created poker-playing bots using MCTS-related techniques which have beaten human world champions. Both of these may be seen as as steps towards Artificial General Intelligence (at least in the sense that they dominated humans in areas where human dominance was expected to continue).
Sectors Creative Economy,Digital/Communication/Information Technologies (including Software)

URL http://mcts.ai/
 
Description We greatly extended the range of decisions that can be modelled through randomised simulations of possible futures to consider situations where there is hidden information (e.g. one player cannot see an aspect of another's state such as their hidden cards) which has the potential to allow many real-world decisions to be modelled as well. Leading UK mobile games developer AI Factory (www.aifactory.co.uk) have used our software in commercial games downloaded over 5 million times (see https://play.google.com/store/apps/details?id=uk.co.aifactory.spadesfree&hl=en_GB). We have presented a keynote jointly with the CEO of AI Factory at the leading industry conference on games development (the Game Developers Conference - www.gdconf.com) and at a leading academic research conferences on game AI (the AAAI conference on Artificial Intelligence in Interactive Digital Entertainment - www.aiide.org). We have presented tutorials at the www.nucl.ai conference in Vienna, the leading focussed conference on commercial game AI, and at the other top academic research conferences on game AI (the IEEE Conference on Computational Intelligence in Games). Following the nucl.ai talk we have anecdotal evidence of our techniques being used in Mcrosoft Games and Creative Assembly. We had a day of face-to-face discussions with Creative Assembly. The techniques discussed are now in the market leading Rome2 game published by Creative Assembly ( see http://aigamedev.com/open/coverage/mcts-rome-ii/). Mining the data from the way that human opponents have played against our AI has provided a new avenue for research into human behaviour and a new way to provide strong and more entertaining players for AI Factory - as presented at the nucl.ai conference alongside AI Factory. This is underpinning a new strand of research in behavioural psychology which we are undertaking within the EPSRC DE Hub project "Digital Creativity Labs". We published 15 papers, including a survey cited 687 times to date (Google Scholar 15th March 2017 - see http://ieeexplore.ieee.org/document/6145622/), an extended article in the top AI journal "Artificial Intelligence" and 5 papers in the top IEEE Transactions on Computational Intelligence and AI in Games. NOTE: from 2018 submission the research and impacts from this project have been picked up by Digital Creativity Labs (EP/M023265/1) Creative Media Labs (AH/S002839/1) and the IGGI Centre for Doctoral Training (EP/L015846/1 and EP/S022325/1) - so further developments will be reported through this route.
First Year Of Impact 2012
Sector Creative Economy,Digital/Communication/Information Technologies (including Software)
Impact Types Cultural,Economic

 
Description Centre for Doctoral Training in Intelligent Games and Game Intelligence
Amount £5,589,505 (GBP)
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 04/2014 
End 09/2022
 
Description Digital Creativity Hub
Amount £4,039,831 (GBP)
Funding ID EP/M023265/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 10/2015 
End 09/2020
 
Description New Economic Models and Opportunities for digital Games
Amount £1,160,895 (GBP)
Funding ID EP/K039857/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom
Start 10/2013 
End 10/2016
 
Description AI Factory Collaboration 
Organisation AI Factory
Country United Kingdom 
Sector Private 
PI Contribution Our decision-making AI technology has been used directly in AI factory's mobile games - and has been downloaded over 5 million times, propelling their implementation of the card game "Spades" to number 1 in the Android charts.
Collaborator Contribution AI Factory provided access to the game's source code, integrated the AI and deployed it in their Spades game. Since deployment they have collected and shared with us a large amount of gameplay data that has been of great use in future research.
Impact The AI we developed helped their implementation of the card game "Spades" reach number 1 in the Google Play Store (Android) charts. Peter Cowling and Jeff Rollason gave a joint Keynote at the world's leading Game Developers Conference in 2014 - and a number of papers were co-published with Jeff Rollason.
Start Year 2011
 
Title mcts.ai 
Description Library for Monte Carlo Tree Search 
Type Of Technology Software 
Year Produced 2013 
Open Source License? Yes  
Impact Work with AI Factory and used in 
 
Description Google's Go triumph is a milestone for artificial intelligence research - Article for the Conversation 
Form Of Engagement Activity A press release, press conference or response to a media enquiry/interview
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Article written for The Conversation by Peter Cowling and Sam Devlin, explaining the impact of Google Deep Mind's success in developing AI to beat the European Go Champion - with strong links to their own research in AI.
The article has been republished many times and shared with more than 200 social media shares.
Year(s) Of Engagement Activity 2016
URL https://theconversation.com/googles-go-triumph-is-a-milestone-for-artificial-intelligence-research-5...
 
Description Let us Play: Artificial and Human Intelligence in Games 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact Public engagement talk on AI and HCI research in Games
Year(s) Of Engagement Activity 2015
 
Description Monte Carlo Tree Search Tutorial 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact An invited tutorial at the IEEE Computational Intelligence in Games conference (IEEE CIG 2012) on the algorithms researched as part of the project
Year(s) Of Engagement Activity 2012
 
Description Monte Carlo Tree Search for Card and Board Games 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact An invited talk at the Vienna Game AI Conference held by AIGameDev.com
Year(s) Of Engagement Activity 2012
 
Description Peter Cowling attended UKIE Westminster reception (with Matt Hancock MP and others) 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact I was invited to a UKIE-hosted reception at Westminster - providing an opportunity to talk about our research to people at Westminster including Noirin Carmody (chair of UKIE), Lynne Kilpatrick (civil servant - Head of Video Games and Creative Industries Skills) and many from the games industry.
Year(s) Of Engagement Activity 2017
URL https://ukie.org.uk/event/2017/10/16/westminster-games-industry-day
 
Description Peter Cowling contributed to Dagstuhl Seminar with leading international experts on "AI-Driven Games Design" 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact A workshop bringing together 30 of the world's leading researchers in AI-Driven game design - to set the agenda for research in this area for the coming decade. I polled 100 industry partners and took along the best research questions coming from that poll.
Year(s) Of Engagement Activity 2017,2018
URL https://www.dagstuhl.de/en/program/calendar/semhp/?semnr=17471
 
Description Rolling the Dice: Leveraging Monte Carlo Tree Search in Game AI 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact An invited talk on the research outputs of the project at the largest industry conference in the area
Year(s) Of Engagement Activity 2014
URL http://schedule2014.gdconf.com/session-id/828005