Rollout sampling approximate policy iteration
Artikel i vetenskaplig tidskrift, 2008

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervised learning problem. This paper proposes variants of an improved policy iteration scheme which addresses the core sampling problem in evaluating a policy through simulation as a multi-armed bandit machine. The resulting algorithm offers comparable performance to the previous algorithm achieved, however, with significantly less computational effort. An order of magnitude improvement is demonstrated experimentally in two standard reinforcement learning domains: inverted pendulum and mountain-car.

Approximate policy iteration

Bandit problems

Rollouts

Reinforcement learning

Classification

Sample complexity

Författare

Christos Dimitrakakis

Chalmers, Data- och informationsteknik, Datavetenskap

M.G. Lagoudakis

Machine Learning

0885-6125 (ISSN) 1573-0565 (eISSN)

Vol. 72 157-171

Styrkeområden

Informations- och kommunikationsteknik

Ämneskategorier

Data- och informationsvetenskap

DOI

10.1007/s10994-008-5069-3