Efficient exploration through active learning for value function approximation in reinforcement learning

Takayuki Akiyama

doi:10.1016/j.neunet.2009.12.010

Efficient exploration through active learning for value function approximation in reinforcement learning

2010-06-01

22

PRE

AI

DOI：10.1016/j.neunet.2009.12.010

Original

Original request for help

Save

Abstract

En 中文

Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares policy iteration (LSPI) framework allows us to employ statistical active learning methods for linear regression. Then we propose a design method of good sampling policies for efficient exploration, which is particularly useful when the sampling cost of immediate rewards is high. The effectiveness of the proposed method, which we call active policy iteration (API), is demonstrated through simulations with a batting robot. (C) 2010 Elsevier Ltd. All rights reserved.

Keywords:

Reinforcement learning

Markov decision process

Least-squares policy iteration

Active learning

Batting robot

Efficient exploration through active learning for value function approximation in reinforcement learning

Abstract

AI Summary

Journal

Organization