Online feature selection for model-based reinforcement learning

Publication Type

Conference Proceeding Article

Publication Date

6-2013

Abstract

We propose a new framework for learning the world dynamics of feature-rich environments in model-based reinforcement learning. The main idea is formalized as a new, factored state-transition representation that supports efficient online-learning of the relevant features. We construct the transition models through predicting how the actions change the world. We introduce an online sparse coding learning technique for feature selection in high-dimensional spaces. We derive theoretical guarantees for our framework and empirically demonstrate its practicality in both simulated and real robotics domains. Copyright 2013 by the author(s).

Keywords

Artificial intelligence; Software engineering High dimensional spaces, Learning techniques, Model-based reinforcement learning, Online feature selection, Relevant features, Theoretical guarantees, Transition model, World dynamics

Discipline

Databases and Information Systems

Publication

Proceedings of The 30th International Conference on Machine Learning

Volume

1

First Page

498

Last Page

506

Publisher

International Machine Learning Society (IMLS)

City or Country

Atlanta, USA

This document is currently not available here.

Share

COinS