Finite model approximations and asymptotic optimality of quantized policies in decentralized stochastic control
Finite model approximations and asymptotic optimality of quantized policies in decentralized stochastic control
复制标题
分散随机控制中量化策略的有限模型近似和渐近最优性
DOI：
10.1109/tac.2016.2613902
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
T. Linder
中科院分区：
文献类型：
--
作者：
Naci Saldi;S. Yüksel;T. Linder
在这篇文章中，我们考虑了一大类静态和动态团队问题的有限模型近似，这些模型是通过对主体的观察空间和动作空间的一致量化来构造的。从这些有限模型得到的策略可以在温和的技术假设下以任意精度逼近最优成本。特别是，量化的团队策略是渐近最优的。然后将这一结果应用于高斯中继信道问题。这一结果也适用于我们先前单独研究过的Witsenhausen的反例。
In this paper, we consider finite model approximations of a large class of static and dynamic team problems where these models are constructed through uniform quantization of the observation and action spaces of the agents. The strategies obtained from these finite models are shown to approximate the optimal cost with arbitrary precision under mild technical assumptions. In particular, quantized team policies are asymptotically optimal. This result is then applied to the Gaussian relay channel problem. This result also applies to Witsenhausen's counterexample, which we had studied individually earlier.