@inproceedings{WZlta18,
    author = {Kyle Hollins Wray and Shlomo Zilberstein},
    title = {Policy Networks for Reasoning in Long-Term Autonomy},
    booktitle = {Proceedings of the AAAI Fall Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy},
    pages = {103--110},
    year = {2018},
    abstract = {Policy networks are graphical models that integrate decision-making models. They allow for multiple Markov decision processes (MDPs) that describe distinct focused aspects of a domain to work in harmony to solve a large-scale problem. This paper presents the formalization of policy networks and their use in modeling reasoning tasks necessary for scalable long-term autonomy. We prove that policy networks generalize a wide array of previous models, such as options and constrained MDPs, which can be equivalently viewed as the integration of multiple models. To illustrate the approach, we apply policy networks to the challenging real world domain of robotic home health care. We demonstrate the benefits of policy networks on a real robot and show how they facilitate scalable integration of multiple decision-making models.}
}