Science & Engineering Research Support soCiety (SERSC)
One of the key questions of the Artificial Intelligence (AI) is the design intelligent agents. The design of intelligent agents by means of reinforcement learning is studied in this paper. A relational reinforcement learning algorithm is used to achieve a compact knowledge representation. Moreover, this approach allows improving the learning performance by augmenting the algorithm with the so-called background knowledge. A case study on simulated physical robotic agents is performed and compared with the authors' previous evolutionary robotics experiments in order to justify their approach.