Genetic reinforcement learning for neurocontrol problems

Darrell Whitley, Stephen Dominic, Rajarshi Das, Charles W. Anderson
1994 Machine Learning  
Empirical tests indicate that at least one class of genetic algorithms yields good performance for neural network weight optimization in terms of learning rates and scalability. The successful application of these genetic algorithms to supervised learning problems sets the stage for the use of genetic algorithms in reinforcement learning problems. On a simulated inverted-pendulum control problem, "genetic reinforcement learning" produces competitive results with AHC, another well-known
more » ... ment learning paradigm for neural networks that employs the temporal difference method. These algorithms are compared in terms of learning rates, performancebased generalization, and control behavior over time.
doi:10.1007/bf00993045 fatcat:m3ybyxp5u5bxpdml5nahpfnyfm