TY - GEN
T1 - Communicating with unknown teammates
AU - Barrett, Samuel
AU - Agmon, Noa
AU - Hazon, Noam
AU - Kraus, Sarit
AU - Stone, Peter
N1 - Publisher Copyright:
© 2014 The Authors and IOS Press.
PY - 2014
Y1 - 2014
N2 - 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, multiarmed 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.
AB - 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, multiarmed 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.
KW - Artificial intelligence
KW - Intelligent systems
KW - Polynomial approximation
KW - Ad-hoc teams
KW - Coordination methods
KW - Limited communication
KW - Multi-armed bandit problem
KW - Number of methods
KW - Number of sources
KW - Polynomial-time
KW - Human resource management
UR - http://www.scopus.com/inward/record.url?scp=84923188815&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-419-0-45
DO - 10.3233/978-1-61499-419-0-45
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84923188815
SN - 9781943580125
T3 - Frontiers in Artificial Intelligence and Applications
SP - 45
EP - 50
BT - ECAI 2014 - 21st European Conference on Artificial Intelligence, Including Prestigious Applications of Intelligent Systems, PAIS 2014, Proceedings
A2 - Schaub, Torsten
A2 - Friedrich, Gerhard
A2 - O'Sullivan, Barry
PB - IOS Press
T2 - 21st European Conference on Artificial Intelligence, ECAI 2014
Y2 - 18 August 2014 through 22 August 2014
ER -