In this paper, we address the complex task of initializing an on-line simulation to a current system state collected from an operating physical system. The paper begins by discuss...
Planning for real-time applications involves decisions not only about what actions to take in what states to progress toward achieving goals (the traditional decision problem face...
Charles B. McVey, Ella M. Atkins, Edmund H. Durfee...
This paper briefly outlines the main characteristics of an ongoing research aimed at developing a support library for implementing systems based on autonomous agents. The library ...
The game of Go has a high branching factor that defeats the tree search approach used in computer chess, and long-range spatiotemporal interactions that make position evaluation e...
Nicol N. Schraudolph, Peter Dayan, Terrence J. Sej...
Abstract. Validation can be used to detect when over tting starts during supervised training of a neural network; training is then stopped before convergence to avoid the over ttin...