Bounded Finite State Controllers
Poupart, Pascal, Boutilier, Craig
–Neural Information Processing Systems
We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic finite state controllers, combining several advantages of gradient ascent (efficiency, search through restricted controller space) and policy iteration (less vulnerability to local optima).
Neural Information Processing Systems
Dec-31-2004