@COMMENT This file was generated by bib2html.pl version 0.90
@COMMENT written by Patrick Riley
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{ALA13-chakrado,
author = {Doran Chakraborty and Noa Agmon and Peter Stone},
title = {Targeted Opponent Modeling of Memory-Bounded Agents},
booktitle = {Proceedings of the Adaptive Learning Agents Workshop (ALA)},
location = {St. Paul, Minnesota, USA},
month = {May},
year = {2013},
abstract = {
In a repeated game, a memory-bounded agent selects its
next action by basing its policy on a fixed window of
past L plays. Traditionally, approaches that attempt to
model memory-bounded agents, do so by modeling them
based on the past L joint actions. Since the number of
possible L sized joint actions grows exponentially with
L, these approaches are restricted to modeling agents
with a small L. This paper explores an alternative, more
efficient mechanism for modeling memory-bounded agents
based on high-level features derived from the past L
plays. Called Targeted Opponent Modeler against
Memory-Bounded Agents, or TOMMBA, our approach
successfully models memory-bounded agents, in a sample
efficient manner, given a priori knowledge of a feature
set that includes the correct features. TOMMBA is fully
implemented, with successful empirical results in a
couple of challenging surveillance based tasks.
},
}