Harrington, Kyle, Awa, Emmanuel, Cussat-Blanc, Sylvain and Pollack, Jordan (2013) Robot Coverage Control by Neuromodulation. In: International Joint Conference on Neural Networks - IJCNN 2013, 4 August 2013 - 9 August 2013, Dallas, United States.

[thumbnail of Harrington_12451.pdf]
Download (529kB) | Preview


An important connection between evolution and learning was made over a century ago and is now termed as the Baldwin effect. Learning acts as a guide for an evolutionary search process. In this study reinforcement learning agents are trained to solve the robot coverage control problem. These agents are improved by evolving neuromodulatory gene regula- tory networks (GRN) that influence the learning and memory of agents. Agents trained by these neuromodulatory GRNs can consistently generalize better than agents trained with fixed parameter settings. This work introduces evolutionary GRN models into the context of neuromodulation and illustrates some of the benefits that stem from neuromodulatory GRNs.

Item Type: Conference or Workshop Item (Paper)
Date: 2013
Uncontrolled Keywords: Evolved neuromodulation - Baldwin effect - Gene regulatory networks
Divisions: Institut de Recherche en Informatique de Toulouse
Site: UT1
Date Deposited: 22 Feb 2019 15:08
Last Modified: 02 Apr 2021 15:59
URI: https://publications.ut-capitole.fr/id/eprint/30148
View Item


Downloads per month over past year