Modular neural networks and reinforcement learning
2004 (English)Report (Other academic)
We investigate the effect of modular architecture in an artificial neural network for a reinforcement learning problem. Using the supervised backpropagation algorithm to solve a two-task problem, the network performance can be increased by using networks with modular structures. However, using a modular architecture to solve a two-task reinforcement learning problem will not increase the performance compared to a non-modular structure. We show that by combining a modular structure with a modular reward signal the network learns significantly faster.
Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2004. no 34, 6 p.
Trita-NA, ISSN 0348-2952 ; 0434
IdentifiersURN: urn:nbn:se:kth:diva-8799OAI: oai:DiVA.org:kth-8799DiVA: diva2:14233
QC 201112162005-11-232005-11-232011-12-16Bibliographically approved