BriefGPT.xyz
Jun, 2011
部分可观察马尔可夫决策过程的值函数逼近
Value-Function Approximations for Partially Observable Markov Decision Processes
HTML
PDF
M. Hauskrecht
TL;DR
本文介绍了部分可观测马尔可夫决策过程(POMDP)的近似（启发式）方法，研究其性质和关系，并提供一些新见解。该理论结果在代理导航领域的问题上得到了实验支持。
Abstract
partially observable markov decision processes
(POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in
stochastic domains
in which states of the system are observ
→