Sciweavers

Share
NIPS
1994

Finding Structure in Reinforcement Learning

8 years 9 months ago
Finding Structure in Reinforcement Learning
Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance inunknownenvironments. Toscale reinforcement learning to complex real-world tasks, such as typically studied in AI, one must ultimately be able ver the structure in the world, in order to abstract away the myriad of details and to operate in more tractable problem spaces. This paper presents the SKILLS algorithm. SKILLS discovers skills, which are partially defined action policies that arise in the context of multiple, related tasks. Skills collapse whole action sequences into single operators. They are learned by minimizing the compactness of action policies, using a description length argument on their representation. Empirical results in simple grid navigation tasks illustrate the successful discovery of structure in reinforcement learning.
Sebastian Thrun, Anton Schwartz
Added 02 Nov 2010
Updated 02 Nov 2010
Type Conference
Year 1994
Where NIPS
Authors Sebastian Thrun, Anton Schwartz
Comments (0)
books