Density-Adaptive Learning and Forgetting

We describe a density-adaptive reinforcement learning and a density-adaptive forgetting algorithm. This learning algorithm uses hybrid k-D/2k-trees to allow for a variable resolution partitioning and labelling of the input space. The density adaptive forgetting algorithm deletes observations from the learning set depending on whether subsequent evidence is available in a local region of the parameter space. The algorithms are demonstrated in a simulation for learning feasible robotic grasp approach directions and orientations and then adapting to subsequent mechanical failures in the gripper. Comments University of Pennsylvania Institute for Research in Cognitive Science Technical Report No. IRCS-93-50. This technical report is available at ScholarlyCommons: http://repository.upenn.edu/ircs_reports/197