Sciweavers

Share
ABIALS
2008
Springer

Anticipatory Learning Classifier Systems and Factored Reinforcement Learning

10 years 4 months ago
Anticipatory Learning Classifier Systems and Factored Reinforcement Learning
Factored Reinforcement Learning (frl) is a new technique to solve Factored Markov Decision Problems (fmdps) when the structure of the problem is not known in advance. Like Anticipatory Learning Classifier Systems (alcss), it is a model-based Reinforcement Learning approach that includes generalization mechanisms in the presence of a structured domain. In general, frl and alcss are explicit, stateanticipatory approaches that learn generalized state transition models to improve system behavior based on model-based reinforcement learning techniques. In this contribution, we highlight the conceptual similarities and differences between frl and alcss, focusing on the one hand on spiti, an instance of frl method, and on alcss, macs and xacs, on the other hand. Though frl systems seem to benefit from a clearer theoretical grounding, an empirical comparison between spiti and xacs on two benchmark problems reveals that the latter scales much better than the former when some combination of state...
Olivier Sigaud, Martin V. Butz, Olga Kozlova, Chri
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2008
Where ABIALS
Authors Olivier Sigaud, Martin V. Butz, Olga Kozlova, Christophe Meyer
Comments (0)
books