AAAI-97 Workshop
on
Multiagent Learning
July 28, 1997
Providence, Rhode Island

Organizing committee members:


SCHEDULE OF PRESENTATIONS

8:30 Introductory Remarks (10 minutes)

SESSION I

8:40 Invited Speaker: Jordan Pollack,
Co-evolution and Mediocrity in Learning

SESSION II

9:40 David C. Parkes and Lyle H. Ungar,

"Learning and Adaption in Multiagent Systems"
Abstract

10:00 Coffee Break (30 minutes)

SESSION III

10:30 Sandip Sen and Neeraj Arora,
"Learning to take risks"
Abstract
10:50 Caroline Claus and Craig Boutilier,
"The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems"
Abstract
11:10 Peter Stone and Manuela Veloso,
"Using Decision Tree Confidence Factors for Multiagent Control"
Abstract
11:30 Tucker Balch,
"Learning Roles: Behavioral Diversity in Robot Teams"
Abstract

11:50 LUNCH (100 minutes)

SESSION IV

1:30 Panel Discussion: "Multiagent learning problems and approaches" Moderator: Sandip Sen

SESSION V

2:30 Oliver Guenther, Tad Hogg and Bernardo A. Huberman,
"Learning in Multiagent Control of Smart Matter"
Abstract
Related material
2:50 Claudia V. Goldman and Jeffrey S. Rosensehein,
"Evolving Organizations of Agents"
Abstract
3:10 Maria Gordin, Narendra Puppala and Sandip Sen,
"Evolving Cooperative Groups: Preliminary Results"
Abstract
3:30 Thomas Haynes,
"Augmenting Collective Adaptation with Simple Process Agents"
Abstract

4:00 Coffee Break (30 minutes)

SESSION VI

4:30 Jose M. Vidal and Edmund H. Durfee,
"Agents Learning about Agents: A Framework and Analysis"
Abstract
4:50 Edwin de Jong,
"An Accumulative Exploration Method for Reinforcement Learning"
Compressed version
Abstract
5:10 M.V. Nagendra Prasad and Victor R. Lesser,
"Learning Problem Solving in Cooperative Multi-agent Systems"
Abstract
5:30 Raj Bhatnagar,
"Learning by Cooperating Agents"

5:50 Concluding Remarks

Sandip Sen's homepage