Autonomous Vehicle Navigation Using Evolutionary Reinforcement Learning
A. Stafylopatis & K. Blekas
Abstract
Reinforcement learning schemes perform direct on-line search in
control space. This makes them appropriate for modifying control
rules to obtain improvements in the performance of a system. The
effectiveness of a reinforcement learning strategy is studied here
through the training of a {\em learning classifier system (LCS)} that
controls the movement of an autonomous vehicle in simulated paths
including left and right turns. The LCS comprises a set of
condition-action rules (classifiers) that compete to control the
system and evolve by means of a genetic algorithm. Evolution and
operation of classifiers depend upon an appropriate credit assignment
mechanism based on reinforcement learning. Performance results for
different design options are obtained and the role of various
parameters is investigated. The performance of vehicle movement
under the proposed evolutionary approach is compared with that of
other (neural) approaches based on reinforcement learning that have
been applied previously to the same benchmark application.