On the convergence of reinforcement learning using a decision tree learner
Jan Ramon · Lirias · 2005
In this paper, we propose conditions under which Q iteration using decision trees for function approximation is guaranteed to converge to the optimal policy in the limit, using only a storage space linear in the size of the decision tree. We analyze different factors that influence the efficiency of the proposed algorithm, and in particular study the efficiency of different concept languages. We illustrate the approach with some preliminary experiments. 1.