Bounded Finite State Controllers
Abstract
We describe a new approximation algorithm for solving partially observ- able MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic finite state controllers, combining sev- eral advantages of gradient ascent (efficiency, search through restricted controller space) and policy iteration (less vulnerability to local optima).
Cite
Text
Poupart and Boutilier. "Bounded Finite State Controllers." Neural Information Processing Systems, 2003.Markdown
[Poupart and Boutilier. "Bounded Finite State Controllers." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/poupart2003neurips-bounded/)BibTeX
@inproceedings{poupart2003neurips-bounded,
title = {{Bounded Finite State Controllers}},
author = {Poupart, Pascal and Boutilier, Craig},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {823-830},
url = {https://mlanthology.org/neurips/2003/poupart2003neurips-bounded/}
}