Modulating reinforcement-learning parameters using agent emotions

Rickard Von Haugwitz, Yoshifumi Kitamura, Kazuki Takashima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

An actor-critic reinforcement-learning algorithm using a radial-basis-function network for approximation of the actor and the critic was run on a small-scale multi-agent system with an initially unpredictably hostile environment. The performance of two approaches was compared: having fixed learning parameters, and using modulated parameters that were allowed to deviate from their base values depending on the simulated emotional state of the agent. The latter approach was shown to give marginally better performance once the distracting hostile elements were removed from the environment. This seems to indicate that emotion-modulated learning may lead to somewhat closer approximation of the optimal policy in a difficult environment, by focusing learning on more useful input and avoiding pursuing suboptimal strategies.

Original languageEnglish
Title of host publication6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012
Pages1281-1285
Number of pages5
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 Joint 6th International Conference on Soft Computing and Intelligent Systems, SCIS 2012 and 13th International Symposium on Advanced Intelligence Systems, ISIS 2012 - Kobe, Japan
Duration: 2012 Nov 202012 Nov 24

Publication series

Name6th International Conference on Soft Computing and Intelligent Systems, and 13th International Symposium on Advanced Intelligence Systems, SCIS/ISIS 2012

Other

Other2012 Joint 6th International Conference on Soft Computing and Intelligent Systems, SCIS 2012 and 13th International Symposium on Advanced Intelligence Systems, ISIS 2012
CountryJapan
CityKobe
Period12/11/2012/11/24

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint Dive into the research topics of 'Modulating reinforcement-learning parameters using agent emotions'. Together they form a unique fingerprint.

Cite this