Аннотация

We consider the convergence of a class of reinforcement learning algorithms combined with value function interpolation methods using the methods developed in (Littman and Szepesvari, 1996). As a special case of the obtained general results, for the first time, we prove the (almost sure) convergence of Q-learning when combined with value function interpolation in uncountable spaces.

Линки и ресурсы

тэги