| Sign In to gain access to subscriptions and/or personal tools. |
B-Learning: A Reinforcement Learning Variant for the Control of a PlantINESC, rua Alves Redol, 9 Apartado 10105 1017 Lisboa Codex, Portugal
Université de Technologie de Compiegne U. R. A. 817 du CNRS BP649 F-60206 Compiègne Cedex, France This paper presents a new reinforcement learning scheme called B-Learning. This approach leads to an estimate of the expected benefits provided by each action with respect to the current policy. This algorithm performs a one-step ahead exhaustive search in the action space and allows the introduction of additional constraints. The method is successfully applied to the control of a water production plant.
Journal of Intelligent Material Systems and Structures, Vol. 5, No. 2,
272-278 (1994) |
|||