Kalise. Mean field control hierarchy. Applied Math Optim., vol. 76, no. 1, pp. 93-135, 2017.Albi G, Choi Y-P, Fornasier M, Kalise D. 2016 Mean field control hier- archy. Applied Mathematics & Optimization, 76(1): 93-135.
We study the optimal control of mean-field systems with heterogeneous and asymmetric interactions. This leads to considering a family of controlled Brownian diffusion processes with dynamics depending on the whole collection of marginal probability laws. We prove the well-posedness of such systems and ...
Next, we are interested in optimal control problems for (fully coupled respectively) FBSDEs of mean-field type with a convex control domain. Note that the control problems are time inconsistent in the sense that the Bellman optimality principle does not hold. The stochastic maximum principle (SMP...
本文属于多智能体强化学习领域,比较了 Cooperative MARL 与 Mean field control (MFC) 之间的关联。我们知道,在 cooperative MARL中,多个智能体为了同一个目标而制定共同的策略 (即它们享有同一个 reward function),当然每一个个体有自己的策略。而如果智能体的数量多到一定的程度,那么它们的 action 就可以不用视为...
This paper considers the problem of partially observed optimal control for forward-backward stochastic systems driven by Brownian motions and an independent Poisson random measure with a feature that the cost functional is of mean-field type. When the coefficients of the system and the objective perfo...
Under some assumptions the optimality conditions for singular mean-field control are reduced to a reflected Skorohod problem, whose solution is proved to exist uniquely. Applications are given to optimal harvesting of stochastic mean-field systems, optimal irreversible investments under uncertainty and to...
“This brief monograph is a presentation of some aspects of MFG theory and of a related class of problems, called mean field type control, where the state of the control system is driven by a McKean-Vlasov equation, namely, a stochastic differential equation where the drift depends also on ...
The SNN technique and mean-field control are merged into one unified framework, B-ACM. The B-ACM includes three regions of neurons in coordination with mean-field control: 1) Reward region to approximate the optimal cost function, 2) MAS Population Estimation region to predict the effects from...
Here, MARL via mean field control (MFC) offers a potential solution to scalability, but fails to consider decentralized and partially observable systems. In this paper, we enable decentralized behavior of agents under partial information by proposing novel models for decentralized partially observable ...
The posterior probability and the optimal control are obtained by solving the Zakai equation and the Bellman equation, respectively. Figure 1. Schematic diagram of (a) completely observable stochastic control (COSC), (b) partially observable stochastic control (POSC), and (c) memory-limited ...