On ensemble techniques for AIXI approximation

Date

2012-12

Authors

Veness, Joel
Sunehag, Peter
Hutter, Marcus

Journal Title

Journal ISSN

Volume Title

Publisher

Springer Verlag

Abstract

One of the key challenges in AIXI approximation is model class approximation - i.e. how to meaningfully approximate Solomonoff Induction without requiring an infeasible amount of computation? This paper advocates a bottom-up approach to this problem, by describing a number of principled ensemble techniques for approximate AIXI agents. Each technique works by efficiently combining a set of existing environment models into a single, more powerful model. These techniques have the potential to play an important role in future AIXI approximations.

Description

Keywords

Ensemble Techniques, AIXI, Universal Artificial Intelligence

Citation

Source

Type

Conference paper

Book Title

Artificial General Intelligence: 5th International Conference, AGI 2012, Oxford, UK, December 8-11, 2012. Proceedings

Entity type

Access Statement

License Rights

Restricted until