Abstract. We present a model of motor learning based on a combination of Operational Space Control and Optimal Control. Anticipatory processes are used both in the learning of the ...
Simulation theories have in recent years proposed that a cognitive agent's "inner world" can at least partly be constituted by internal emulations or simulations of ...
Abstract. In order to establish autonomous behavior for technical systems, the well known trade-off between reactive control and deliberative planning has to be considered. Within ...
Factored Reinforcement Learning (frl) is a new technique to solve Factored Markov Decision Problems (fmdps) when the structure of the problem is not known in advance. Like Anticipa...
Olivier Sigaud, Martin V. Butz, Olga Kozlova, Chri...