Seminar Announcement
These events are organized by various sub-sets of the IEEE Toronto Section.
The contact person listed below is the volunteer who has arranged this event.
Please use the e-mail link provided if you have any questions, suggestions,
or concerns.
| Title
|
Playing Games With N-Tuple Systems
|
| Speaker
|
Prof. Simon M. Lucas
School of Computer Science and Electronic Engineering
University of Essex (UK)
|
| Day and Time
|
Wednesday, September 29, 2010, 10:00 a.m. – 11:30 p.m. (EDT) (i.e., Toronto, Ontario)
Wednesday, September 29, 2010, 3:00 p.m. – 4:30 p.m. (GMT) (i.e., London, UK)
For all other locations, please, check the actual time in your time zone. If you are not sure, you can use this Time Zone Converter
Please, login at least 15 minutes earlier to check your connection and make sure that you are ready to attend the talk when it begins |
| Location
|
Online Webinar (see registration below)
|
| Webinar
|
Registration is free but it is required..
After registering you will receive a confirmation email containing information about joining the Webinar.
System Requirements:
PC-based attendees
Required: Windows® 2000, XP Home, XP Pro, 2003 Server, Vista
Macintosh®-based attendees
Required: Mac OS® X 10.4 (Tiger®) or newer
|
| Registration |
Space is limited. Reserve your Webinar seat now at:
https://www2.gotomeeting.com/register/815434083
|
| Organizer
|
|
|
|
|
| Contact
|
Anna T. Lawniczak. E-mail:
|
| Abstract |
When learning to play any non-trivial game, function approximation plays an essential role (either implicitly or explicitly) in controlling the behaviour of the learning agent and can greatly affect how well the agent learns.
This talk will explain the use of n-tuple systems for function approximation in this context. They work by sub-sampling the input space and storing learned values directly in tables (n-tuple systems are also known as RAM-based neural networks).
N-tuple systems date back to the late 1950s and offer very rapid learning together with good quality function approximation when applied appropriately.
Examples will be covered of applying n-tuples to game learning in discrete and in continuous input spaces, with the newly developed interpolated n-tuple systems being used for the latter. I will also describe how to use these in conjunction with temporal difference learning algorithms.
| | Biography |
Simon M. Lucas (SMIEEE) is a professor of computer science at the University of Essex (UK), where he leads the game intelligence group. He is the founding editor-in-chief of the IEEE Transactions on Computational Intelligence and AI in Games. His main research interests are evolutionary computation, games, and pattern recognition, and he has published widely in these fields with over 130 peer-reviewed papers. He was chair of IAPR Technical Committee 5 on Benchmarking and Software (2002 - 2006) and is the inventor of the scanning n-tuple classifier, a fast and accurate OCR method. Professor Lucas has chaired or co-chaired many international conferences, including the first IEEE Symposium on Computational Intelligence and Games in 2005. He is an associated editor of the IEEE Transactions on Evolutionary Computation, and the Springer Journal of Memetic Computing. He was an invited keynote speaker or tutorial speaker at IEEE CEC 2007, IEEE WCCI 2008, IEEE CIG 2008, PPSN 2008, and IEEE CEC 2009.
http://dces.essex.ac.uk/staff/lucas/
|
|
