A Study on the Control of Nonlinear System Using Growing RBFN and Reinforcement Learning

The proposed approach is neural-network based and combines the self-tuning principle with reinforcement learning. The proposed control scheme consists of a controller, a utility estimator, an exploration module, a learning module and a rewarding module. The controller and the utility estimator are implemented together in a single radial basis function network (RBFN). The learning method involves structural adaptation (growing RBFN) and parameter adaptation. No prior knowledge of the plant is assumed, and the controller has to begin with exploration of the state space. The exploration versus exploitation dilemma of reinforcement learning is solved through smooth transitions between the two modes. The controller is capable of asymptotically approaching the desired reference trajectory, which is showed in simulation result.