Robot Coverage Control by Neuromodulation - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Robot Coverage Control by Neuromodulation

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 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.
Fichier principal
Vignette du fichier
Harrington_12451.pdf (615.8 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01147304 , version 1 (30-04-2015)

Identifiers

  • HAL Id : hal-01147304 , version 1
  • OATAO : 12451

Cite

Kyle Harrington, Emmanuel Awa, Sylvain Cussat-Blanc, Jordan Pollack. Robot Coverage Control by Neuromodulation. International Joint Conference on Neural Networks - IJCNN 2013, Aug 2013, Dallas, United States. pp. 1-8. ⟨hal-01147304⟩
60 View
82 Download

Share

Gmail Facebook X LinkedIn More