Matthew E. Taylor's Publications

Sorted by DateClassified by Publication TypeSorted by First Author Last NameClassified by Research Category

Preliminary Results for 1 vs. 1 Tactics in Starcraft

Nicholas Carboni and Matthew E. Taylor. Preliminary Results for 1 vs. 1 Tactics in Starcraft. In Proceedings of the Adaptive and Learning Agents workshop (at AAMAS-13), May 2013.
ALA-13

Download

[PDF]386.5kB  

Abstract

This paper describes the development and analysis of two algorithmsdesigned to allow one agent, the teacher, to give advice toanother agent, the student. These algorithms contribute to a familyof algorithms designed to allow teaching with limited advice.We compare the ability of the student to learn using reinforcementlearning with and without such advice. Experiments are conductedin the Starcraft domain, a challenging but appropriate domain forthis type of research. Our results show that the time at which adviceis given has a significant effect on the result of student learning andthat agents with the best performance in a task may not always bethe most effective teachers.

BibTeX Entry

@inproceedings(ALA13-Carboni,
  author="Nicholas Carboni and Matthew~E.\ Taylor",
  title="Preliminary Results for 1 vs.~1 Tactics in Starcraft",
  Booktitle="Proceedings of the Adaptive and Learning Agents workshop (at AAMAS-13)",
  month="May",
  year= "2013",
  wwwnote={<a href="http://swarmlab.unimaas.nl/ala2013/">ALA-13</a>},
 abstract="This paper describes the development and analysis of two algorithms
designed to allow one agent, the teacher, to give advice to
another agent, the student. These algorithms contribute to a family
of algorithms designed to allow teaching with limited advice.
We compare the ability of the student to learn using reinforcement
learning with and without such advice. Experiments are conducted
in the Starcraft domain, a challenging but appropriate domain for
this type of research. Our results show that the time at which advice
is given has a significant effect on the result of student learning and
that agents with the best performance in a task may not always be
the most effective teachers.",
)

Generated by bib2html.pl (written by Patrick Riley ) on Thu Jul 24, 2014 16:09:11