|
Published Articles >> Table of Contents >> Abstract
Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 2 (AAMAS'04)
pp. 538-545
The Role of Reactivity in Multiagent Learning
Bikramjit Banerjee, Tulane University
Jing Peng, Tulane University
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AAMAS.2004.10131
Send link to a friend
| Abstract |
|
In this paper we take a closer look at a recently proposed
classification scheme for multiagent learning algorithms.
Based on this scheme an exploitation mechanism
(we call it the Exploiter) was developed that could beat various
Policy Hill Climbers (PHC) and other fair opponents
in some repeated matrix games. We show on the contrary
that some fair opponents may actually beat the Exploiter in
repeated games. This clearly indicates a deficiency in the
original classification scheme which we address. Specifically, we introduce a new measure called Reactivity that
measures how fast a learner can adapt to an unexpected hypothetical
change in the opponent’s policy. We show that in
some games, this new measure can approximately predict
the performance of a player, and based on this measure we
explain the behaviors of various algorithms in the Matching
Pennies game, which was inexplicable by the original
scheme. Finally we show that under certain restrictions, a
player that consciously tries to avoid exploitation may be
unable to do so.
|
 Additional Information
|
Citation:
Bikramjit Banerjee, Jing Peng,
"The Role of Reactivity in Multiagent Learning,"
aamas,
pp. 538-545,
Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 2 (AAMAS'04),
2004
|
|
