Temporal difference learning with interpolated table value functions

摘要

This paper introduces a novel function approximation architecture especially well suited to temporal difference learning. The architecture is based on using sets of interpolated table look-up functions. These offer rapid and stable learning, and are efficient when the number of inputs is small. An empirical investigation is conducted to test their performance on a supervised learning task, and on themountain car problem, a standard reinforcement learning benchmark. In each case, the interpolated table functions offer competitive performance.