Genetic reinforcement learning for neural networks
- 9 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. ii, 71-76 vol.2
- https://doi.org/10.1109/ijcnn.1991.155315
Abstract
It is pointed out that the genetic algorithms which have been shown to yield good performance for neural network weight optimization are really genetic hill-climbers, with a strong reliance on mutation rather than hyperplane sampling. Neural control problems are more appropriate for these genetic hill-climbers than supervised learning applications because in reinforcement learning applications gradient information is not directly available. Genetic reinforcement learning produces competitive results with the adaptive heuristic critic method, another reinforcement learning paradigm for neural networks that employs temporal difference methods. The genetic hill-climbing algorithm appears to be robust over a wide range of learning conditions.<>Keywords
This publication has 5 references indexed in Scilit:
- Genetic algorithms and neural networks: optimizing connections and connectivityParallel Computing, 1990
- Learning to control an inverted pendulum using neural networksIEEE Control Systems Magazine, 1989
- Learning to predict by the methods of temporal differencesMachine Learning, 1988
- Strategy Learning with Multilayer Connectionist RepresentationsPublished by Elsevier ,1987
- Neuronlike adaptive elements that can solve difficult learning control problemsIEEE Transactions on Systems, Man, and Cybernetics, 1983