Division of Informatics
Forrest Hill & 80 South Bridge
Research Paper #881 | |
|---|---|
| Title: | Emotion-Driven Learning for Animat Control |
| Authors: | Gadanho,S; Hallam,JC |
| Date: | Jan 1998 |
| Presented: | To be presented at SAB 98 - 5th International Conference of the Society of Adaptive Behavior |
| Keywords: | |
| Abstract: | Models of emotion are often suggested as a way of providing an evaluation of the current behaviour of an agent. In this work, we investigate whether emotions can actually provide suitable reinforcement signals for a Q-learning system to learn adaptive policies. For this purpose a recurrent network model of emotion consistent with the somatic marker hypothesis of Damasio was developed. Experimental work was done in a realistic mobile robot simulator in a simple foraging-like task. Experiments revealed that having emotions providing a context evaluation for direct use as a reinforcement signal does not work, but using them as modifiers for learning system parameters could be fruitful. |
| Download: | POSTSCRIPT COPY |
![[Search These Pages]](http://www.dai.ed.ac.uk/icons/dai_search.gif){kind=icon}
![[DAI Home Page]](http://www.dai.ed.ac.uk/icons/dai_home.gif){kind=icon}
![[Comment]](http://www.dai.ed.ac.uk/icons/dai_comment.gif){kind=icon}