Print Email Facebook Twitter Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework Title Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework Author Van Vliet, B. Contributor Jonker, P.P. (mentor) Schuitema, E. (mentor) Faculty Mechanical, Maritime and Materials Engineering Department BioMechanical Engineering Programme BMD/Biorobotics Date 2010-10-28 Abstract Learning a motor skill task with Reinforcement Learning still takes a long time. A way to speed up the learning process with- out using much prior knowledge is to use sub-goals. In this study, the use of subgoals decreased the learning time by a factor nine and we show that tests on a real robot give similar results. The price to be paid, in case the subgoals do not lie on the optimal path, is a worse end performance. Hierarchical greedy execution can (partially) cancel out this problem. For future work, we suggest the use of a method which is able to obtain optimal performance. Subject Reinforcement To reference this document use: http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce Embargo date 2010-12-15 Part of collection Student theses Document type master thesis Rights (c) 2010 Van Vliet, B. Files PDF Thesis_Bart_van_Vliet.pdf 8.94 MB Close viewer /islandora/object/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce/datastream/OBJ/view