Multiagent reinforcement learning problems are especially difficult because of their dynamism and the size of joint state space. In this paper a new benchmark problem is proposed, ...
Abstract. A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization met...
Georg Schneider, Heiko Wersing, Bernhard Sendhoff,...
Words unknown to the lexicon present a substantial problem to part-of-speech tagging. In this paper we present a technique for fully unsupervised statistical acquisition of rules ...
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...
We consider the minimization of a smooth loss with trace-norm regularization, which is a natural objective in multi-class and multitask learning. Even though the problem is convex...