Demonstration of Learned Helplessness with Fuzzy Reinforcement Learning
Vali Derhami1, Zahra Youhannaei
1Electrical and Computer Department, Yazd University,
Available Online December 2008.
- 10.2991/jcis.2008.8How to use a DOI?
- Learned helplessness, Fuzzy systems, Reinforcement learning
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.
- © 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/).
Cite this article
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 -