TY - GEN
T1 - Coordinate to cooperate or compete
T2 - 38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016
AU - Kleiman-Weiner, Max
AU - Ho, Mark K.
AU - Austerweil, Joseph L.
AU - Littman, Michael L.
AU - Tenenbaum, Joshua B.
N1 - Publisher Copyright:
© 2016 Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. All rights reserved.
PY - 2016
Y1 - 2016
N2 - Successfully navigating the social world requires reasoning about both high-level strategic goals, such as whether to cooperate or compete, as well as the low-level actions needed to achieve those goals. While previous work in experimental game theory has examined the former and work on multi-agent systems has examined the later, there has been little work investigating behavior in environments that require simultaneous planning and inference across both levels. We develop a hierarchical model of social agency that infers the intentions of other agents, strategically decides whether to cooperate or compete with them, and then executes either a cooperative or competitive planning program. Learning occurs across both high-level strategic decisions and low-level actions leading to the emergence of social norms. We test predictions of this model in multi-agent behavioral experiments using rich video-game like environments. By grounding strategic behavior in a formal model of planning, we develop abstract notions of both cooperation and competition and shed light on the computational nature of joint intentionality.
AB - Successfully navigating the social world requires reasoning about both high-level strategic goals, such as whether to cooperate or compete, as well as the low-level actions needed to achieve those goals. While previous work in experimental game theory has examined the former and work on multi-agent systems has examined the later, there has been little work investigating behavior in environments that require simultaneous planning and inference across both levels. We develop a hierarchical model of social agency that infers the intentions of other agents, strategically decides whether to cooperate or compete with them, and then executes either a cooperative or competitive planning program. Learning occurs across both high-level strategic decisions and low-level actions leading to the emergence of social norms. We test predictions of this model in multi-agent behavioral experiments using rich video-game like environments. By grounding strategic behavior in a formal model of planning, we develop abstract notions of both cooperation and competition and shed light on the computational nature of joint intentionality.
KW - cooperation
KW - coordination
KW - joint intention
KW - reinforcement learning
KW - teams
UR - http://www.scopus.com/inward/record.url?scp=85093324404&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85093324404&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85093324404
T3 - Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016
SP - 1679
EP - 1684
BT - Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016
A2 - Papafragou, Anna
A2 - Grodner, Daniel
A2 - Mirman, Daniel
A2 - Trueswell, John C.
Y2 - 10 August 2016 through 13 August 2016
ER -