TY - GEN
T1 - Learning to identify winning coalitions in the PAC model
AU - Procaccia, Ariel D.
AU - Rosenschein, Jeffrey S.
PY - 2006
Y1 - 2006
N2 - We consider PAG learning of simple cooperative games, in which the coalitions are partitioned into "winning" and "losing" coalitions. We analyze the complexity of learning a suitable concept class via its Vapnik-Chervonenkis (VC) dimension, and provide an algorithm that learns this class. Furthermore, we study constrained simple games; we demonstrate that the VC dimension can be dramatically reduced when one allows only a single minimum winning coalition (even more so when this coalition has cardinality 1), whereas other interesting constraints do not significantly lower the dimension.
AB - We consider PAG learning of simple cooperative games, in which the coalitions are partitioned into "winning" and "losing" coalitions. We analyze the complexity of learning a suitable concept class via its Vapnik-Chervonenkis (VC) dimension, and provide an algorithm that learns this class. Furthermore, we study constrained simple games; we demonstrate that the VC dimension can be dramatically reduced when one allows only a single minimum winning coalition (even more so when this coalition has cardinality 1), whereas other interesting constraints do not significantly lower the dimension.
KW - Coalition formation
KW - PAC learning
UR - http://www.scopus.com/inward/record.url?scp=34247192566&partnerID=8YFLogxK
U2 - 10.1145/1160633.1160751
DO - 10.1145/1160633.1160751
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:34247192566
SN - 1595933034
SN - 9781595933034
T3 - Proceedings of the International Conference on Autonomous Agents
SP - 673
EP - 675
BT - Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems
T2 - Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Y2 - 8 May 2006 through 12 May 2006
ER -