Reinforcement Learning and Dynamic Optimization

Abstract

This paper is about optimization achieved through reinforced learning. First, the concept of an augmented value function for infinite horizon discounted dynamic programs is defined. Next, the issue of convergence and the speed of the convergence in the context of a cakeeating problem are studied. Finally, in numerical simulations it is observed that regardless of initial beliefs learning of the augmented value function and hence optimal behavior is attainable within reasonable time horizons under the presence of experimentation and slow cooling. JEL Classification Codes: D83, D91.