Predictive projections

Authors:
Nathan Sprague
Affiliations:
Kalamazoo College, Kalamazoo, MI
Venue:
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Year:
2009

Citing 5
Cited 1

Least-squares policy iteration

The Journal of Machine Learning Research
Action respecting embedding

ICML '05 Proceedings of the 22nd international conference on Machine learning
Automatic basis function construction for approximate dynamic programming and reinforcement learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes

The Journal of Machine Learning Research
An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning

Proceedings of the 25th international conference on Machine learning

Construction of approximation spaces for reinforcement learning

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the problem of learning control policies in very high dimensional state spaces. We propose a linear dimensionality reduction algorithm that discovers predictive projections: projections in which accurate predictions of future states can be made using simple nearest neighbor style learning. The goal of this work is to extend the reach of existing reinforcement learning algorithms to domains where they would otherwise be inapplicable without extensive engineering of features. The approach is demonstrated on a synthetic pendulum balancing domain, as well as on a robot domain requiring visually guided control.