liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
A Dynamic Tree Structure for Incremental Reinforcement Learning of Good Behavior
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.ORCID iD: 0000-0002-9091-4724
1994 (English)Report (Other academic)
Abstract [en]

This paper addresses the idea of learning by reinforcement, within the theory of behaviorism. The reason for this choice is its generality and especially that the reinforcement learning paradigm allows systems to be designed, which can improve their behavior beyond that of their teacher. The role of the teacher is to define the reinforcement function, which acts as a description of the problem the machine is to solve. Gained knowledge is represented by a behavior probability density function which is approximated with a number of normal distributions, stored in the nodes of a binary tree. It is argued that a meaningful partitioning into local models can only be accomplished in a fused space consisting of both stimuli and responses. Given a stimulus, the system searches for responses likely to result in highly reinforced decisions by treating the sum of the two normal distributions on each level in the tree as a distribution describing the system's behavior at that resolution. The resolution of the response, as well as the tree growing and pruning processes, are controlled by a random variable based on the difference in performance between two consecutive levels in the tree. This results in a system that will never be content but will indefinitely continue to search for better solutions.

Place, publisher, year, edition, pages
Linköping, Sweden: Linköping University, Department of Electrical Engineering , 1994. , 12 p.
LiTH-ISY-R, ISSN 1400-3902 ; 1628
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-53421ISRN: LiTH-ISY-R-1628OAI: diva2:288270
Available from: 2010-01-20 Created: 2010-01-20 Last updated: 2014-09-15Bibliographically approved

Open Access in DiVA

fulltext(163 kB)206 downloads
File information
File name FULLTEXT01.pdfFile size 163 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Knutsson, Hans
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 206 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 402 hits
ReferencesLink to record
Permanent link

Direct link