Finding Structure in Reinforcement Learning

Finding Structure in Reinforcement Learning (1995)

Cached

Download Links

[ktm.ius.cs.cmu.edu]
[www-2.cs.cmu.edu]

Other Repositories/Bibliography

DBLP

by Sebastian Thrun , Anton Schwartz

Venue:	Advances in Neural Information Processing Systems 7
Citations:	98 - 4 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Finding Structure in Reinforcement Learning	user correction - Legacy Corrections
AUTHOR NAME	Sebastian Thrun	SVM HeaderParse 0.1
AUTHOR AFFIL	University of Bonn; Department of Computer Science III	SVM HeaderParse 0.2
AUTHOR ADDR	Romerstr. 164, D-53117 Bonn, Germany	SVM HeaderParse 0.1
AUTHOR NAME	Anton Schwartz	SVM HeaderParse 0.1
AUTHOR AFFIL	Dept. of Computer Science; Stanford University	SVM HeaderParse 0.2
AUTHOR ADDR	Stanford, CA 94305	SVM HeaderParse 0.1
ABSTRACT	Reinforcement learning addresses the problem of learning to select actions in order to maximize one's performance in unknown environments. To scale reinforcement learning to complex real-world tasks, such as typically studied in AI, one must ultimately be able to discover 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. 1 Introduction Reinforcement learning comprises a family of incremental planning algorithms that construct reactive con...	user correction - Legacy Corrections
YEAR	1995	INFERENCE
VENUE	Advances in Neural Information Processing Systems 7	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	385--392	INFERENCE
VOLUME	7	INFERENCE
CITATIONS	15 found	ParsCit 1.0