Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Cooperating with a Markovian Ad Hoc Teammate

Doran Chakraborty and Peter Stone. Cooperating with a Markovian Ad Hoc Teammate. In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2013.

Download

[PDF]202.3kB  [postscript]408.2kB  

Abstract

This paper focuses on learning in the presence of a Markovian teammate in Ad hoc teams. A Markovian teammate's policy is a function of a set of discrete feature values derived from the joint history of interaction, where the feature values transition in a Markovian fashion on each time step. We introduce a novel algorithm "Learning to Cooperate with a Markovian teammate", or LCM, that converges to optimal cooperation with any Markovian teammate, and achieves safety with any arbitrary teammate. The novel aspect of LCM is the manner in which it satisfies the above two goals via efficient exploration and exploitation. The main contribution of this paper is a full specification and a detailed analysis of LCM's theoretical properties.

BibTeX Entry

@InProceedings{AAMAS13-chakrado,
  author = {Doran Chakraborty and Peter Stone},
  title = {Cooperating with a Markovian Ad Hoc Teammate},
  booktitle = {Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
  location = {St. Paul, Minnesota, USA},
  month = {May},
  year = {2013},
  abstract = {
              This paper focuses on learning in the presence of a
              Markovian teammate in Ad hoc teams. A Markovian
              teammate's policy is a function of a set of discrete
              feature values derived from the joint history of
              interaction, where the feature values transition in a
              Markovian fashion on each time step. We introduce a
              novel algorithm "Learning to Cooperate with a Markovian
              teammate", or LCM, that converges to optimal
              cooperation with any Markovian teammate, and achieves
              safety with any arbitrary teammate. The novel aspect of
              LCM is the manner in which it satisfies the above two
              goals via efficient exploration and exploitation. The
              main contribution of this paper is a full specification
              and a detailed analysis of LCM's theoretical properties.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Aug 15, 2014 16:26:03