Approximate Policy Iteration with Linear Action Models

• DOI: 10.1609/aaai.v26i1.8319
• Publication Date: 2022-06-01T20:35:27Z
• Authors: Hengshuai Yao; Csaba Szepesvari
• Keywords: 0502 economics and business; 05 social sciences

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.