摘要
The properties of a learning-based system are particularly relevant to the process study of the unknown behavior of a system or environment. In the semiconductor industry, there is regularly a partially observable system in which the entire state of the process is not directly or fully visible due to uncertainties or disturbances. The model for studying such a system that permits uncertainties regarding the stochastic (Markov) process for state information acquisition is called a partially observable Markov decision process (POMDP). This study aims to deal with the optimization issue of compensation control bias of a dynamic multilayer lithography process in wafer fabrication with prior information, the existence of high-dimensionality, and unmeasurable uncertainties. We show how the POMDP on a linear state-space model with uncertainties can encode the information from past runs and layers, and deal with accumulated overlay error at the current run and layer. The Gibbs sampling is applied to optimize the belief function of POMDP optimization approach.