Abstract
Transfer learning is the process of using knowledge gained while solving one problem to solve a new, previously un-encountered problem. Current research has concentrated on analogical transfer – a mechanic is able to fix a type of car he has never seen before by comparing it to cars he has fixed before. This approach is typical of case-based reasoning systems and has been successful on a wide variety of prob-lems[Watson, 1997]. When a new problem is encountered,a database of previously solved problems is searched for a problem with similar features. The solution to the most sim-ilar problem is selected, adapted and then applied to the new problem. Similar methods exist for adapting reinforcement learning policies [Taylor and Stone, 2009]