Communicating with Unknown Teammates

被引:16
作者
Barrett, Samuel [1 ]
Agmon, Noa [2 ]
Hazon, Noam [3 ]
Kraus, Sarit [2 ,4 ]
Stone, Peter [1 ]
机构
[1] Univ Texas Austin, Austin, TX 78712 USA
[2] Bar Ilan Univ, Ramat Gan, Israel
[3] Arid l Univ, Rawalpindi, Pakistan
[4] Univ Maryland, College Pk, MD 20742 USA
来源
21ST EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE (ECAI 2014) | 2014年 / 263卷
关键词
D O I
10.3233/978-1-61499-419-0-45
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:45 / +
页数:2
相关论文
共 20 条
[1]  
[Anonymous], 1999, The TAEMS White Paper
[2]   Finite-time analysis of the multiarmed bandit problem [J].
Auer, P ;
Cesa-Bianchi, N ;
Fischer, P .
MACHINE LEARNING, 2002, 47 (2-3) :235-256
[3]  
Barrett Samuel, 2012, AAMAS 12 JUN
[4]  
Bowling M., 2005, AAAI
[5]  
Doshi Prashant, 2009, AAMAS 09
[6]   A framework for sequential planning in multi-agent settings [J].
Gmytrasiewicz, PJ ;
Doshi, P .
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2005, 24 :49-79
[7]  
Goldman Claudia V., 2007, AUTONOMOUS AGENTS MU, V15
[8]  
GROSZ B, 1999, FDN THEORIES RATIONA
[9]  
Hsu D., 2007, NIPS
[10]  
Kocsis Levente., 2006, ECML-06