Robot reinforcement learning accuracy-based learning classifier systems with Fuzzy Policy Gradient descent(XCS-FPGRL)

This paper presented a novel approach XCS-FPGRL to research on robot reinforcement learning. XCS-FPGRL combines covering operator and genetic algorithm. The systems is responsible for adjusting precision and reducing search space according to some reward obtained from the environment, acts as an innovation discovery component which is responsible for discovering new better reinforcement learning rules. The experiment and simulation showed that robot reinforcement learning can achieved convergence very quickly.