Meeting Agenda

Date:	August 18th, 2004
Location:	DC 1304
Time:	2:30 PM
Chair:	Jie Xu

1. Adoption of the Agenda - additions or deletions

2. Coffee Hour

Coffee hour last week:

Sylvain

Coffee hour this week:

???

Coffee hour next week:

???

3. Forthcoming

Date:	August 25th	September 1st	September 8th	September 15th
Location:	DC2303	DC1304	DC1304	DC1304
Chair:	Mike Watch-your-left-ski	Daming Yao	Bryan Chan	Alex Clarke
Technical  Presentation:	Mike Watch-your-left-ski	Jie Xu	Edwin Vane	Daming Yao

4. Technical Presentation

Kevin Moule

Title:COLLADA: A Brief Introduction

Abstract: COLLADA is an interchange format for digital assest exchange. It was showcased at this year's SIGGRAPH. I will be briefly discussing the internals of the format, touching on some of the novel and interesting features.

5. General Discussion Items

• DC1304 not available for lab meeting on Aug 25. Please keep this until that time.
• Network update: Firewall is being set up and backups are complete.

6. Action List

• Lab rearrangement

7. Conferences and Special Journal Issues

8. Directors' Meeting

9. Seminars and Events

Monday, 16 August 2004, 10:30AM - Computer Science , DC 1304

Arash Farzan: -- Cache-Oblivious Searching and Sorting in Multisets
 

Tuesday, 17 August 2004, 2:30PM - Computer Science (Algorithms and Complexity Group), DC 1304

Michael Spriggs: -- Angles and Lengths in Reconfigurations of Polygons and Polyhedra
 

Wednesday, 18 August 2004, 1:30PM - Computer Science , DC 1304

Bradford Hovinen: -- Blocked Lanczos-style Algorithms over Small Finite Fields
 

Wednesday, 18 August 2004, 2:00PM - Computer Science (Artifical Intelligence Group), DC 2306C

Michael Bowling: -- PM Wednesday 18 August 2004 Computer Science Dept., University of Alberta Wednesday, 18 August 2004 48 28 14 13 7 104 5 225 1 wlrush cs Seminar DC 2306C false true Artifical Intelligence Group 129.97.74.97 wlrush Michael Bowling Learning in a multiagent system is a challenging problem due to two key factors. First, if other agents are simultaneously learning then the environment is no longer stationary, thus undermining convergence guarantees. Second, learning is often susceptible to deception, where the other agents may be able to exploit a learner's particular dynamics. In the worst case, this could result in poorer performance than if the agent was not learning at all. These challenges are identifiable in the two most common evaluation criteria for multiagent learning algorithms: convergence and regret. Algorithms focusing on convergence or regret in isolation are numerous. In this talk, I seek to address both criteria in a single algorithm by introducing GIGA-WoLF, a learning algorithm for normal-form games. The algorithm guarantees at most zero average regret, and converges in many situations of self-play, with both theoretical and empirical evidence. Finally, these results also suggest a third new learning criterion combining convergence and regret, called subzero regret. Convergence and No-Regret in Multiagent Learning Convergence and No-Regret in Multiagent Learning Convergence and No-Regret in Multiagent Learning Convergence and No-Regret in Multiagent LearningConvergence and No-Regret in Multiagent Learning 2:00PM 2004 7 18 14 00 0

10. Lab Cleanup !