R-HybrID: Evolution of agent controllers with a hybridisation of indirect and direct encodings

Neuroevolution, the optimisation of artificial neural networks (ANNs) through evolutionary computation, is a promising approach to the synthesis of controllers for autonomous agents. Traditional neuroevolution approaches employ direct encodings, which are limited in their ability to evolve complex o...

Full description

Bibliographic Details
Main Author: Silva, F. (author)
Other Authors: Correia, L. (author), Christensen, A. (author)
Format: conferenceObject
Language:eng
Published: 2022
Subjects:
Agent controller
Artificial neural network
Evolutionary computation
Genetic encoding
Neuroevolution
Online Access:http://hdl.handle.net/10071/25116
Country:Portugal
Oai:oai:repositorio.iscte-iul.pt:10071/25116

Internet

http://hdl.handle.net/10071/25116

Similar Items