A new approach of adaptive reinforcement learning control

A new learning algorithm for connectionist networks that solves a class of optimal control problems is presented. The algorithm, called adaptive reinforcement learning algorithm, employs a second network to model immediate reinforcement provided from the task environment and adaptively identify it through experience. Output perturbation and correlation techniques are used to translate mere critic signals into useful learning signals for the connectionist controller. Compared with the direct approaches of reinforcement learning, this algorithm shows faster and guaranteed improvement in the control performance. Robustness against inaccuracy of the model is also discussed.