Large Decentralized Continuous-Time Convex Stochastic Teams and Their Mean-Field Limits

We study a class of continuous-time convex stochastic exchangeable teams with a finite number of decision makers (DMs) as well as their mean-field limits with infinite numbers of DMs. We establish the existence of a globally optimal solution and show that it is Markovian and symmetric (identical) for both the finite DM regime and the infinite one. In particular, for a general class of finite-
$N$
exchangeable stochastic teams satisfying a convexity condition, we establish the existence of a globally optimal solution that is symmetric among DMs and Markovian. As the number of DMs drives to infinity (that is for the mean-field limit), we establish the existence of a possibly randomized globally optimal solution and show that it is symmetric among DMs and Markovian.