We address classification problems for which the training instances are governed by a distribution that is allowed to differ arbitrarily from the test distribution--problems also ...
There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...
— A decentralized controller is presented that causes a network of robots to converge to a near optimal sensing configuration, while simultaneously learning the distribution of ...
Mac Schwager, Jean-Jacques E. Slotine, Daniela Rus
Recent psychological and neurological evidence suggests that biological object recognition is a process of matching sensed images to stored iconic memories. This paper presents a p...
Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...