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
Collections
Source
Type
Conference paper
Book Title
Artificial General Intelligence: 5th International Conference, AGI 2012, Oxford, UK, December 8-11, 2012. Proceedings