Genomic computing networks learn complex POMDPs

Authors:
David Montana;Eric VanWyk;Marshall Brinn;Joshua Montana;Stephen Milligan
Affiliations:
BBN Technologies, Cambridge, MA;BBN Technologies, Cambridge, MA;BBN Technologies, Cambridge, MA;BBN Technologies, Cambridge, MA;BBN Technologies, Cambridge, MA
Venue:
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Year:
2006

Citing 4
Cited 0

Long short-term memory

Neural Computation
Evolving neural networks through augmenting topologies

Evolutionary Computation
Attribute grammar encoding of the structure and behaviour of artificial neural networks

Attribute grammar encoding of the structure and behaviour of artificial neural networks
Co-evolving recurrent neurons learn deep memory POMDPs

GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A genomic computing network is a variant of a neural network for which a genome encodes all aspects, both structural and functional, of the network. The genome is evolved by a genetic algorithm to fit particular tasks and environments. The genome has three portions: one for specifying links and their initial weights, a second for specifying how a node updates its internal state, and a third for specifying how a node updates the weights on its links. Preliminary experiments demonstrate that genomic computing networks can use node internal state to solve POMDPs more complex than those solved previously using neural networks.