Demonstration of Learned Helplessness with Fuzzy Reinforcement Learning

DOI

10.2991/jcis.2008.8How to use a DOI?

Keywords

Learned helplessness, Fuzzy systems, ‎Reinforcement learning‎

Abstract

This paper demonstrates a kind of learned ‎helplessness in human being that is ap-‎peared in Fuzzy Reinforcement Learning ‎‎(FRL) algorithm. At the beginning of ‎learning, when an agent continuously per-‎forms actions that cause sequential pun-‎ishments, afterwards it does not usually ‎behave well and often selects actions that ‎evoke punishments. This faulty learning ‎is similar to what is called learned help-‎lessness in social sciences. Here, this ‎problem is demonstrated in training an ‎agent by FRL algorithm. By analyzing ‎this problem, a new reinforcement func-‎tion for prevention is presented. ‎

Copyright

© 2008, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Vali Derhami
AU  - Zahra Youhannaei
PY  - 2008/12
DA  - 2008/12
TI  - Demonstration of Learned Helplessness with Fuzzy Reinforcement Learning
BT  - Proceedings of the 11th Joint Conference on Information Sciences (JCIS 2008)
PB  - Atlantis Press
SP  - 48
EP  - 53
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2008.8
DO  - 10.2991/jcis.2008.8
ID  - Derhami2008/12
ER  -