[Seminar] Perfect, Immortal Machines: The Future Of Automated Game Design

The Game AI Group at Queen Mary University of London has the pleasure to receive Dr. Micheal Cook for a seminar talk at 4pm on March 14th.
Get a ticket to secure your spot at the event!


Title: Perfect, Immortal Machines: The Future Of Automated Game Design
Speaker: Dr Michael Cook (http://www.gamesbyangelina.org/)
Time: 4pm-5pm (GMT), Mar 14, 2018
Room: Graduate Center 201, EECS, QMUL
Coffee/tea/cakes will be served at 3:30pm in the hub, wine and nibbles will be served in the hub after the seminar.

It’s a golden age for AI in games – they can play them, they can generate content for them, they can even design them. But what does this really mean for games culture? Is AI doomed to live in a dark room and only come out when we ask it to play Go?
In this talk, computational creativity researcher Michael Cook talks about the history of the future of automated game design; his latest work on his game designing AI ANGELINA; and explains how the future of AI isn’t a captive algorithm in a box, but an independent digital creative, with its own agenda, its own dreams, and its own Twitch channel.

Slides: http://www.gamesbyangelina.org/talks/qmul.pdf

[Seminar] “Combining Evolution and Learning” by Chrisantha Fernando (Google DeepMind)

The Game AI Group at Queen Mary University of London has the pleasure to receive Chrisantha Fernando for a seminar talk at 4pm on March 20th.
Get a ticket to secure your spot at the event!

Title: Combining Evolution and Learning
Speaker: Dr Chrisantha Fernando, Google DeepMind
Time: 4pm-5pm (GMT), Mar 20, 2018
Room: David Sizer Lecture Theater, Bancroft Building, EECS, QMUL
Drinks/reception: 5pm – 6pm – Informatics Hub, Computer Science Building

Chrisantha Fernando is currently a senior research scientist at Google DeepMind. He has previously been a lecturer at Queen Mary University of London, after having worked on models of the origin of life and Darwinian neurodynamics. He started his career as a medical doctor.


To find more information about the aspects presented in this talk, have a look at the links below:

General Video Game AI tutorial at QMULGRADFEST

This tutorial is aimed to introduce the concept of general game Artificial Intelligence through the General Video Game AI (GVGAI) framework. The event will begin with a talk describing the higher-level concepts and give an idea about the research carried out in the field, then narrowing down to the specific challenge at hand.

Refreshments, lunch and networking opportunities will be provided as part of the event.

This event is organised by PhD student, Raluca Gaina within the context of QMUL GrasFest.

Slides can be found at here.

Other useful links:

[Seminar] “Computational Creativity and Videogame Design ” by Prof. Simon Colton

Title: Computational Creativity and Videogame Design 

Speaker: Prof. Simon Colton, Digital Games Technologies (Falmouth) and Computational Creativity (Goldsmiths), EPSRC Leadership Fellow Metamakers Institute, Games Academy, Falmouth University Computational Creativity Group, Goldsmiths, University of London.

Time: 5pm-6pm (GMT), Jan 23, 2018
Room: BR3.02, Bancroft Road, School of Electronic Engineering and Computer Science, QMUL


In Computational Creativity research, we try to hand over creative responsibilities to software in arts and science projects, so that our systems can become trusted co-creators or autonomous creatives. After describing some recent advances and issues in Computational Creativity, I’ll move on to what is a killer application for the field, namely videogame design. I’ll describe recent work I’ve been involved with that aims to use AI techniques to democratise game design, so that anyone and everyone can make digital games as easily as they can write stories or make videos. I’ll also cover projects in procedural content generation and whole game design, and the idea that we can communicate our lives through play. At the end of the talk, I’ll come back to Computational Creativity research in general and look at high-level issues such as software showing intentionality, which we’ve addressed through The Painting Fool project. I’ll then describe what I believe is the biggest issue facing the field, namely authenticity, and I’ll provide some suggestions for how we can start to address this issue.



Simon Colton is a Professor of Digital Games Technology, holding an ERA Chair at Falmouth University, and a part-time Professor of Computational Creativity at Goldsmiths, University of London. He was previously a reader in Computational Creativity at Imperial College, London, and held an EPSRC Leadership Fellowship until mid-2017. An AI researcher for 20 years, he is one of the founding members of the Computational Creativity movement, with nearly 200 publications and national and international awards for his research. At Falmouth, he co-leads the MetaMakers Institute (www.metamakersinstitute.com) applying Computational Creativity techniques to the democratisation of game design and the cultural appreciation of videogames. At Goldsmiths, he co-leads the Computational Creativity group (ccg.doc.gold.ac.uk), addressing issues of creative behaviour in various application domains. He is also involved in the EPSRC IGGI doctoral training centre and the DC Labs Next Step Digital Economy centre. He is best known for his work on software such as the HR mathematical discovery system, The Painting Fool (www.thepaintingfool.com), the What-If Machine (http://ccg.doc.gold.ac.uk/research/whim) and the Wevva iOS game design system (https://itunes.apple.com/gb/app/wevva/id1322519841 and www.wevvagame.com). He has recently co-founded up a company called Imaginative AI Ltd., to pursue commercial applications of Computational Creativity.

Useful links: metamakers.falmouth.ac.ukccg.doc.gold.ac.ukmetamakersinstitute.comwevvagame.com

EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI)

12 fully-funded PhD studentships to start September 2018

Covers fees at Home/EU rate and a stipend for four years

IGGI is an exciting opportunity for you to undertake a four-year PhD in Intelligent Games and Game Intelligence, working with top games companies and world-leading academics in games research. We currently have 46 students conducting interdisciplinary research in areas such as:
•Artificial Intelligence (AI) to create interesting, fun, believable game agents,
•emotion and immersion in games,
•interaction design for games,
•Machine Learning (ML) to understand player psychology
•using games for learning and wellbeing,
•game audio, graphics and animation
•game design, citizen science and gamification,
•procedural content generation,
•AI-assisted game design and testing.
IGGI is a collaboration between the University of York, the University of London (Goldsmiths and Queen Mary) and the University of Essex. The programme trains PhD researchers who will become the next generation of leaders in research, design, development and entrepreneurship in digital games.
We have 12 studentships available for 2018/19 entry, which will fund full fees (at a Home/EU rate) plus a tax-free living stipend, for a 4-year PhD programme. Could you join our large and growing group of games researchers in the world’s largest games research programme?
IGGI gives you the opportunity to work with our industry partners, allowing you the possibility to contribute directly to the future of games. You will have the opportunity to undertake industrial placements during the IGGI programme, giving you first-hand experience of the games industry. These placements will contribute to your research, ensuring its relevance, as well as giving you the skills needed to succeed in a career in the games industry or games research.
Our students have completed, or are currently on, placements with partner companies such as Sony Interactive Entertainment, Bossa Studios, Google, Bloomberg, Prowler.io, MediaMolecule, BT, SplashDamage, and MindArk. Other partners include organisations such as Electronic Arts, Creative Assembly, Rebellion, Revolution, AI Factory and over 50 games companies and organisations which use games in creative ways (see http://www.iggi.org.uk/industry-partners/).
Your research work with partners like these will advance the creation of more fun and profitable games that exploit research advances, and help to increase the use of games as tools for research in behavioural science and for societal benefit.
You’ll also learn through teamwork and inspiring events such as:
•the IGGI Game Jam, a 48 hour game development challenge as part of the Global
Game Jam, enhancing your skills in game design, development, and teamwork;
•the IGGI Conference, showcasing student research alongside industry and academic speakers;
•student-led events such as the IGGI Game Creator’s Club, research seminars, games evenings.
You’ll receive focused skills training from a range of academic research leaders, covering topics including Games Development, Games Design and Research Skills as well as a range of optional topics in areas such as AI, HCI, graphics, audio and design.

Apply for IGGI

We have 12 fully-funded studentships to award to outstanding students which cover fees and an annual tax-free stipend of £14,553 (or £16,000 with London weighting if studying at Goldsmiths or Queen Mary) for four years (at 2017/18 rates – this is likely to increase slightly for September 2018 starters).

An IGGI application should consist of a CV, a covering letter explaining your motivation and suitability for the IGGI programme, and a statement of your planned research and proposed supervisor(s). You will also be asked for evidence of your programming skills during the application process, either through your qualifications, previous employment or examples of games you have developed.
You can contact potential supervisors directly (see http://www.iggi.org.uk/supervisors/ for a list), or contact us at the email address below and we can help you to choose a principal supervisor from York, Essex, Goldsmiths, or Queen Mary based on your interests and background. We expect substantial competition for IGGI studentships and we encourage good students
to submit applications as early as possible. The deadline for applications is 23:59 (GMT) on Wednesday 31st January 2018. Interviews will take place at University of York on Friday 16th March 2018.
Your CV, covering letter, supervisor information and statement of planned research should be emailed to apply@iggi.org.uk. Please send enquiries to the same email address.

IGGI students are a diverse group, and admission judgements are made exclusively on the basis of experience and potential to do excellent research and contribute to IGGI’s goals. We especially welcome applications from female and minority ethnic candidates as well as other groups that are under-represented in areas related to IGGI.

[Seminar] “Bridge: a new challenge for AI?” by Dr. Véronique Ventos

Title: Bridge: a new challenge for AI?

Speaker: Dr. Véronique Ventos, Associate Professor at University of Paris-Saclay (France)

Date & Time: 4pm, 12th December 2017

Room: Eng3.24, Engineering Building, QMUL Mile End campus (building 15 on the campus map)

As usual, refreshments will be served before and after the seminar in the hub. Please register for helping preparing the refreshments.


Games have always been an excellent field of experimentation for the nascent techniques in computer science and in different areas of Artificial Intelligence (AI) including Machine Learning (ML). Despite their complexity, game problems are much easier to understand and to model than real life problems. Systems initially designed for games are then used in the context of real applications. In the last decades, designs of champion-level systems dedicated to a game (game AI) were considered as milestones of computer science and AI.
Go and Poker are the two most recent successes. In May 2017, AlphaGo (DeepMind) defeated by 3 to 0 the Go world champion Ke Jie. In January 2017, the Poker AI Libratus (Carnegie Mellon University) won a heads-up no-limit Texas hold’em poker event against four of the best professional players.
This success has not yet happened with regard to another incomplete information cards game, namely Bridge, which then provides a challenging problem for AI.
We think that Deep Learning (DL) cannot be the only AI future. There are many Machine Learning and more generally AI fields which can interact with DL. Bridge is a great example of an application needing more than black box approaches. The AlphaBridge project is dedicated to the design of a Bridge AI taking up this challenge by using hybrid framework in the field of Artificial Intelligence.
The first part of the webinar is devoted to the presentation of the different aspects of bridge and of various challenges inherent to it. In a second part, we will present our work concerning the optimization of the AI Wbridge5 developed by Yves Costel. This work is based on a recent seed methodology (T. Cazenave, J. Liu and O. Teytaud 2015, 2016) which optimizes the quality of Monte-Carlo simulations and which has been defined and validated in other games. The Wbridge5 version boosted with this method won the World Computer-Bridge Championship twice, in September 2016 and in August 2017. Finally, the last part is about various ongoing works related to the design of a hybrid architecture entirely dedicated to bridge using recent numeric and symbolic Machine Learning modules.


PhD in Artificial Intelligence (Knowledge Representation and Machine Learning) in 1997.
Associate professor at University Paris Saclay, France since 1998. Before joining in 2015 the group A&O in the interplay of Machine Learning and Optimization, she worked in the group LaHDAK (Large-scale Heterogeneous DAta and Knowledge) at Laboratory of Computer Science (LRI).
She started playing bridge in 2004 and is now 59th French woman player out of 48644 players.
In 2015, she set up the AlphaBridge project combining her two passions. AlphaBridge is dedicated to solve the game of bridge by defining a hybrid architecture including recent numeric and symbolic Machine Learning modules.


Useful links
If you don’t know Bridge and want to know how to learn it: http://www.learn2playbridge.com/
If you want to play Bridge online: https://www.bridgebase.com/

[Seminar] “Computer Hanabi: Playing Near-Optimally or Learning by Reinforcement ?” by Dr. Bruno Bouzy

Speaker: Dr. Bruno Bouzy, Associate Professor,  Laboratory of Informatics Paris Descartes (LIPADE), Université Paris Descartes, Paris, France.
Time and date: 4pm, 17th October 2017 (Tuesday)
Title: Computer Hanabi: Playing Near-Optimally or Learning by Reinforcement ?
Room: Eng3.24, Engineering Building, QMUL
Free registration will be highly appreciated as it will be helpful for booking refreshment.
Refreshment will be served before and after the seminar (3:30pm and 5:05pm) in the hub of  Bancroft Road Teaching Rooms10, Godward Square, Queen Mary University of London, London E1 4FZ


Hanabi is a multi-player cooperative card game in which a player sees the cards of the other players but not his own cards. The team of players aims at maximizing a score. After a brief presentation of the rules of the game, this talk will describe two sets of experiments. The first one is an exploitation experiment (how to play as well as possible ?) and the second one explores some pros and cons of the reinforcement learning approach.

The first part will describe computer players corresponding to the state-of-the-art in computer Hanabi. Particularly, we will describe players using the hat principle and depth-one search. The hat principle is well-known in recreational mathematics and gives amazing results on the game of Hanabi, resulting in scores that are almost perfect.

In front of this, the new trend about deep learning led us to perform a second set of experiments to build reinforcement learners using neural networks – not necessarily deep – as function approximators. Hanabi being an incomplete information game, the preliminary results with self-play and shallow neural networks show that the game of Hanabi is a hard game to tackle with a learning approach. We will present our results and discuss the features of the game of Hanabi such as the number of players, the number of cards per player, the possibility to play with open cards or not, the problem of learning a convention, that make this game a good opportunity to test many techniques of reinforcement learning: with TD learning or with Q learning, the use of a replay memory or not, the number of layers in the network, and tuning considerations on the gradient descent.


Born in Paris (France), Bruno Bouzy is Assistant Professor of Computer Science in the Department of Mathematics and Computer Science at the Paris Descartes University since 1997, and in the Laboratory of Informatics of PAris DEscartes (LIPADE) since its creation in 2005. His academic degrees include two engineering school diplomas (Ecole Polytechnique 1984, Ecole Nationale Supérieure des Techniques Avancées, 1986), a Ph.D. in Computer Science (1995) and an Habilitation for Research Supervising in Computer Science (2004). Between 1986 and 1991, he held a consulting engineer position with GSI, a leading software advisory company. Bruno Bouzy is the author of the Go playing program Indigo which won three bronze medals at the computer olympiads: two on 19×19 board (2004, 2006), and one on 9×9 board (2005). These achievements resulted from using the Monte-Carlo (MC) approach for the first time in a competitive Go playing program: playing out simulations until the end, and computing action values with the outcomes of the simulations. After these promising results, the Computer Go community adopted the MC approach, and the Monte-carlo Tree Search (MCTS) framework was created in 2006, and became the standard approach for many games. Since 2007, Bruno Bouzy took a step back from Computer Go – all Go playing progams were MCTS based programs – and moved to other interesting and difficult challenges such as Multi-Agent Learning (2008-2010), the game of Amazons (2004-2010), the Voronoi game (2009-2011), Cooperative Path-Finding (2012-now), the game of Hex (2013), the Rubik’s cube (2014), the weak Schur problem (2014-2015), the Pancake problem (2015-2016). Today, the incomplete information games remaining hard obstacles for Artificial Intelligence, Bruno Bouzy works on the game of Hanabi, a cooperative card game. Practically, to obtain results as good as possible in all these domains, Bruno Bouzy uses various methods such as Game Theory, Heuristic Search, MCTS, Neural Networks, Reinforcement Learning, and domain dependent tools as well.