In this paper we derive convergence rates for Q-learning. We show an interesting relationship between the convergence rate and the learning rate used in Q-learning. For a polynomi...
In the CLear project we develop a cooperative learning system for supporting learning and training processes of co-located and distributed groups. One of the fundamental concepts o...
Most of the work which attempts to give bounds on the generalization error of the hypothesis generated by a learning algorithm is based on methods from the theory of uniform conve...
We investigate the differences of the influences between robot and virtual learning companions on students' engagement. From the analysis of our experimental result and inter...
Modern teaching tools, such as educational robotics, require new learning environments. The teacher especially needs to be supported in novel ways. Conflative learning environment...