Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...
Usually, in a group decision context, the importance level, confidence degree and amount of knowledge are very different among individuals. So, when all the individuals have to r...
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
We consider a networked control system, where each subsystem evolves as a Markov decision process (MDP). Each subsystem is coupled to its neighbors via communication links over wh...