Approximate Policy Iteration with Linear Action Models

In this paper we consider the problem of finding a good policy given some batch data. We propose a new approach, LAM- API, that first builds a so-called linear action model (LAM) from the data and then uses the learned model and the collected data in approximate policy iteration (API) to find a good policy. A natural choice for the policy evaluation step in this algorithm is to use least-squares temporal difference (LSTD) learning algorithm. Empirical results on three benchmark problems show that this particular instance of LAM- API performs competitively as compared with LSPI, both from the point of view of data and computational efficiency.

Authors

• Hengshuai Yao Department of Computing Science, University of Alberta, Edmonton, Canada
• Csaba Szepesvari

Keywords

No keywords are indexed for this paper.