Path-finding using reinforcement learning and affective states

Johannes Feldmaier, Klaus Diepold

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

During decision making and acting in the environment humans appraise decisions and observations with feelings and emotions. In this paper we propose a framework to incorporate an emotional model into the decision making process of a machine learning agent. We use a hierarchical structure to combine reinforcement learning with a dimensional emotional model. The dimensional model calculates two dimensions representing the actual affective state of the autonomous agent. For the evaluation of this combination, we use a reinforcement learning experiment (called Dyna Maze) in which, the agent has to find an optimal path through a maze. Our first results show that the agent is able to appraise the situation in terms of emotions and react according to them.

Original languageEnglish
Title of host publicationIEEE RO-MAN 2014 - 23rd IEEE International Symposium on Robot and Human Interactive Communication
Subtitle of host publicationHuman-Robot Co-Existence: Adaptive Interfaces and Systems for Daily Life, Therapy, Assistance and Socially Engaging Interactions
EditorsRui Loureiro, Aris Alissandrakis, Adriana Tapus, Selma Sabanovic, Fumihide Tanaka, Yukie Nagai
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages543-548
Number of pages6
ISBN (Electronic)9781479967636
DOIs
StatePublished - 15 Oct 2014
Event23rd IEEE International Symposium on Robot and Human Interactive Communication, IEEE RO-MAN 2014 - Edinburgh, United Kingdom
Duration: 25 Aug 201429 Aug 2014

Publication series

NameIEEE RO-MAN 2014 - 23rd IEEE International Symposium on Robot and Human Interactive Communication: Human-Robot Co-Existence: Adaptive Interfaces and Systems for Daily Life, Therapy, Assistance and Socially Engaging Interactions

Conference

Conference23rd IEEE International Symposium on Robot and Human Interactive Communication, IEEE RO-MAN 2014
Country/TerritoryUnited Kingdom
CityEdinburgh
Period25/08/1429/08/14

Fingerprint

Dive into the research topics of 'Path-finding using reinforcement learning and affective states'. Together they form a unique fingerprint.

Cite this