TY - GEN
T1 - Constrained Mean-Field-Type Games
T2 - 58th IEEE Conference on Decision and Control, CDC 2019
AU - Barreiro-Gomez, Julian
AU - Tembine, Hamidou
N1 - Funding Information:
Authors gratefully acknowledge support from U.S. Air Force Office of Scientific Research under grant number FA9550-17-1-0259.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - In this paper, we study a class of constrained mean-field-type games with several decision-makers interacting in a stationary environment. The payoff functionals depend not only on the strategy profile but also on the first moment. This novel static game approach leads to risk-aware solution concepts. We introduce several solution concepts: mean-field-type best-response strategies, mean-field-type generalized Nash equilibria, mean-field-type variational equilibria. We provide a structure of payoffs with a decomposition that includes variance-aware cost. We discuss some learning algorithms to reach mean-field-type best Nash equilibria under constraints. The methodology is extended to include migration costs and migration incentives for each decision-maker and each choice component.
AB - In this paper, we study a class of constrained mean-field-type games with several decision-makers interacting in a stationary environment. The payoff functionals depend not only on the strategy profile but also on the first moment. This novel static game approach leads to risk-aware solution concepts. We introduce several solution concepts: mean-field-type best-response strategies, mean-field-type generalized Nash equilibria, mean-field-type variational equilibria. We provide a structure of payoffs with a decomposition that includes variance-aware cost. We discuss some learning algorithms to reach mean-field-type best Nash equilibria under constraints. The methodology is extended to include migration costs and migration incentives for each decision-maker and each choice component.
UR - http://www.scopus.com/inward/record.url?scp=85082472251&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082472251&partnerID=8YFLogxK
U2 - 10.1109/CDC40024.2019.9029483
DO - 10.1109/CDC40024.2019.9029483
M3 - Conference contribution
AN - SCOPUS:85082472251
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 2208
EP - 2213
BT - 2019 IEEE 58th Conference on Decision and Control, CDC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 11 December 2019 through 13 December 2019
ER -