Robot coverage control by evolved neuromodulation

Item Type:	Conference or Workshop Item
Title:	Robot coverage control by evolved neuromodulation
Creators Name:	Harrington, K.I. and Awa, E. and Cussat-Blanc, S. and Pollack, J.
Abstract:	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 regulatory 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.
Source:	Proceedings of the International Joint Conference on Neural Networks
Title of Book:	The 2013 International Joint Conference on Neural Networks (IJCNN)
ISSN:	2161-4393
ISBN:	978-1-4673-6129-3
Publisher:	IEEE
Page Range:	1-8
Date:	9 January 2014
Official Publication:	https://doi.org/10.1109/IJCNN.2013.6706784

Repository Staff Only: item control page