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...
— As mobile robots become increasingly autonomous over extended periods of time, opportunities arise for their use on repetitive tasks. We define and implement behaviors for a c...
The validation of functional and real-time requirements of control software for embedded systems is a difficult task. It usually needs the electronic control unit (ECU) and the co...
Abstract-- This paper presents a method for creating evaluation functions that efficiently promote coordination in a multiagent system, allowing single-agent evolutionary computati...
In this paper we propose an evolutionary approach capable of successfully combining rules to play the popular video game, Ms. PacMan. In particular we focus our attention on the be...