User: Guest  Login
Document type:
Konferenzbeitrag 
Contribution type:
Poster 
Author(s):
Feldmaier, Johannes; Meyer, Dominik, Shen, Hao; Diepold, Klaus 
Title:
Reinforcement Learning with Preferences 
Pages contribution:
143 - 147 
Abstract:
In this work, we propose a framework of learning with preferences, which combines some neurophysiological findings, prospect theory, and the classic reinforcement learning mechanism. Specifically, we extend the state representation of reinforcement learning with a multi-dimensional preference model controlled by an external state. This external state is designed to be independent from the reinforcement learning process so that it can be controlled by an external process simulating the knowled...    »
 
Keywords:
Preference learning, prospect theory, affective state, reinforcement learning 
Dewey Decimal Classification:
620 Ingenieurwissenschaften 
Book / Congress title:
The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making 
Congress (additional information):
Edmonton, Alberta, Canada 
Date of publication:
09.06.2015 
Year:
2015 
Year / month:
2015-06 
Month:
Jun 
Reviewed:
ja 
Language:
en 
Publication format:
WWW