Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games.

René Carmona Kenza Hamidouche Mathieu Laurière Zongjun Tan

Published in: CDC (2020)

Keyphrases

game theory
nash equilibria
stochastic games
linear quadratic
boolean games
em algorithm
optimal policy
game theoretic
nash equilibrium
markov random field
closed loop
repeated games
vector valued
dynamic programming
color images
real time
incomplete information
average reward
markov decision processes
special case