Benutzer: Gast  Login
Titel:

Reinforcement Learning with Preferences

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Poster
Autor(en):
Feldmaier, Johannes; Meyer, Dominik, Shen, Hao; Diepold, Klaus
Seitenangaben Beitrag:
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 knowledg...     »
Stichworte:
Preference learning, prospect theory, affective state, reinforcement learning
Dewey-Dezimalklassifikation:
620 Ingenieurwissenschaften
Kongress- / Buchtitel:
The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making
Kongress / Zusatzinformationen:
Edmonton, Alberta, Canada
Publikationsdatum:
09.06.2015
Jahr:
2015
Jahr / Monat:
2015-06
Monat:
Jun
Reviewed:
ja
Sprache:
en
Erscheinungsform:
WWW
 BibTeX