Architecture of Knowledge-based Function Approximator

Abstract

This paper proposes a new architecture to build a hybrid value function estimation based on a combination of temporal-different (TD) and on-line variant of Random Forest (RF). We call this implementation Random-TD. The approach iteratively improves its value function by exploiting only relevant parts of action space. We evaluate the potential of the proposed procedure in terms of a reduction in the Bellman error. The results demonstrate that our approach can significantly improve the performance of TD methods and speed up learning process.