We introduce an approach to autonomously creating state space abstractions for an online reinforcement learning agent using a relational representation. Our approach uses a tree-b...
A key problem in reinforcement learning is finding a good balance between the need to explore the environment and the need to gain rewards by exploiting existing knowledge. Much ...
Abstract—Service requests are the origin of every service provisioning process and therefore the entities to be considered first. Similar to Physics and Engineering Sciences, ser...
Recently, quite a few papers studied methods for representing network properties by assigning informative labels to the vertices of a network. Consulting the labels given to any t...
Object recognition and detection represent a relevant component in cognitive computer vision systems, such as in robot vision, intelligent video surveillance systems, or multi-mod...
Gerald Fritz, Christin Seifert, Lucas Paletta, Hor...