Looking at articles or conference papers published since the turn of the century, Pareto optimization is the dominating assessment method for multi-objective nonlinear optimization problems. However, is it always the method of choice for real-world applications, where either more than four objectives have to be considered, or the same type of task is repeated again and again with only minor mod...

This paper describes an approach to reinforcement learning in multiagent general-sum games in which a learner is told to treat each other agent as either a \friend" or \foe". This Q-learning-style algorithm provides strong convergence guarantees compared to an existing Nash-equilibrium-based learning rule.

We speed up marginal inference by ignoring factors that do not significantly contribute to overall accuracy. In order to pick a suitable subset of factors to ignore, we propose three schemes: minimizing the number of model factors under a bound on the KL divergence between pruned and full models; minimizing the KL divergence under a bound on factor count; and minimizing the weighted sum of KL d...