A Binary Competition Tree for Reinforcement Learning
1994 (English)Report (Other academic)
A robust, general and computationally simple reinforcement learning system is presented. It uses a channel representation which is robust and continuous. The accumulated knowledge is represented as a reward prediction function in the outer product space of the input- and output channel vectors. Each computational unit generates an output simply by a vector-matrix multiplication and the response can therefore be calculated fast. The response and a prediction of the reward are calculated simultaneously by the same system, which makes TD-methods easy to implement if needed. Several units can cooperate to solve more complicated problems. A dynamic tree structure of linear units is grown in order to divide the knowledge space into a sufficiently number of regions in which the reward function can be properly described. The tree continuously tests split- and prune criteria in order to adapt its size to the complexity of the problem.
Place, publisher, year, edition, pages
Linköping, Sweden: Linköping University, Department of Electrical Engineering , 1994. , 19 p.
LiTH-ISY-R, ISSN 1400-3902 ; 1623
National CategoryEngineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-53405ISRN: LiTH-ISY-R-1623OAI: oai:DiVA.org:liu-53405DiVA: diva2:288288