Coward, L AndrewGedeon, Tamas (Tom)Ratnayake, Uditha2015-12-132015-12-13July 25-291780383532http://hdl.handle.net/1885/82835The reasons why machine learning appears limited to relatively simple control problems are analyzed. A primary issue is that any condition detected by a learning system acquires multiple behavioural meanings. As learning continues, the need to preserve these meanings severely constrains the architectural form of the system. A hybrid architecture called the recommendation architecture in which the preservation of such meanings is explicitly managed is compared with a wide range of alternative learning approaches. It is concluded that systems with this recommendation architecture have the capability to learn to solve complex control problems.Keywords: Control problems; Look-up table; Operational complexity; Reinforcement learning; Algorithms; Electric power systems; Expert systems; Fuzzy sets; Machine design; Neural networks; Pattern recognition; Probability distributions; Problem solving; Vectors; Lea200410.1109/FUZZY.2004.13755312015-12-11