Abstract— Groups of reinforcement learning agents interacting in a common environment often fail to learn optimal behaviors. Poor performance is particularly common in environmen...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Abstract. The implementation of high-performance robot controllers for complex control tasks such as playing autonomous robot soccer is tedious, errorprone, and a never ending prog...
Abstract. Virtual training systems are increasingly used for the training of complex, dynamic tasks. To give trainees the opportunity to train autonomously, intelligent agents are ...
Presenting information to an e-learning environment is a challenge, mostly, because ofthe hypertextlhypermedia nature and the richness ofthe context and information provides. This...