Samuel Barrett's Publications

Sorted by DateClassified by Publication TypeClassified by TopicSorted by First Author Last Name

Communicating with Unknown Teammates

Samuel Barrett, Noa Agmon, Noam Hazon, Sarit Kraus, and Peter Stone. Communicating with Unknown Teammates. In Proceedings of the Twenty-First European Conference on Artificial Intelligence, August 2014.

Download

[PDF]215.9kB  [slides]1.4MB  

Abstract

Past research has investigated a number of methods for coordinating teams of agents, but with the growing number of sources of agents, it is likely that agents will encounter teammates that do not share their coordination methods. Therefore, it is desirable for agents to adapt to these teammates, forming an effective ad hoc team. Past ad hoc teamwork research has focused on cases where the agents do not directly communicate. However when teammates do communicate, it can provide a valuable channel for coordination. Therefore, this paper tackles the problem of communication in ad hoc teams, introducing a minimal version of the multiagent, multi-armed bandit problem with limited communication between the agents. The theoretical results in this paper prove that this problem setting can be solved in polynomial time when the agent knows the set of possible teammates. Furthermore, the empirical results show that an agent can cooperate with a variety of teammates following unknown behaviors even when its models of these teammates are imperfect.

BibTeX

@InProceedings{ECAI14-Barrett,
  author = {Samuel Barrett and Noa Agmon and Noam Hazon and Sarit Kraus and Peter Stone},
  title = {Communicating with Unknown Teammates},
  booktitle = {Proceedings of the Twenty-First European Conference on Artificial Intelligence},
  location = {Prague, Czech Republic},
  month = {August},
  year = {2014},
  abstract={
    Past research has investigated a number of methods for coordinating teams of
    agents, but with the growing number of sources of agents, it is likely that
    agents will encounter teammates that do not share their coordination
    methods.  Therefore, it is desirable for agents to adapt to these
    teammates, forming an effective ad hoc team.  Past ad hoc teamwork research
    has focused on cases where the agents do not directly communicate.  However
    when teammates do communicate, it can provide a valuable channel for
    coordination.  Therefore, this paper tackles the problem of communication
    in ad hoc teams, introducing a minimal version of the multiagent,
    multi-armed bandit problem with limited communication between the agents.
    The theoretical results in this paper prove that this problem setting can
    be solved in polynomial time when the agent knows the set of possible
    teammates.  Furthermore, the empirical results show that an agent can
    cooperate with a variety of teammates following unknown behaviors even when
    its models of these teammates are imperfect.
  }
}

Generated by bib2html.pl (written by Patrick Riley ) on Sat Sep 02, 2017 19:34:22