Bounded Finite State Controllers

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).

Authors

• Pascal Poupart University of Waterloo Vector Institute
• Craig Boutilier Google Research

Keywords

No keywords are indexed for this paper.