The options framework provides a method for reinforcement learning agents to build new high-level skills. However, since options are usually learned in the same state space as the...
The concept of the Virtual University offers a new learning environment for distance education. All the functionalities of a conventional university are available to the students ...
We address the problem of learning classifiers for several related tasks that may differ in their joint distribution of input and output variables. For each task, small
The human ability to learn difficult object categories from just a few views is often explained by an extensive use of knowledge from related classes. In this work we study the use...
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...