Abstract. We present a system for automatically evolving neural networks as physics-based locomotion controllers for humanoid characters. Our approach provides two key features: (a...
Evolutionary relationships among species can be represented by a phylogenetic tree and inferred by optimising some measure of fitness, such as the statistical likelihood of the t...
Masaccio is a formal model for hybrid dynamical systems which are built from atomic discrete components (di erence equations) and atomic continuous components (di erential equation...
Designing and planning of the switching, signaling and support network is a fairly complex process in cellular mobile network. In this paper, the problem of assigning cells to swi...
Computing a good policy in stochastic uncertain environments with unknown dynamics and reward model parameters is a challenging task. In a number of domains, ranging from space ro...