AAAI Publications, Twenty-Sixth AAAI Conference on Artificial Intelligence

Font Size: 
Approximate Policy Iteration with Linear Action Models
Hengshuai Yao, Csaba Szepesvari

Last modified: 2012-07-14


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.


approximate policy iteration; planning; LSPI

Full Text: PDF