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...
We describe a machine model for automatically dynamizing static algorithms and apply it to historyindependent data structures. Static programs expressed in this model are dynamize...
Umut A. Acar, Guy E. Blelloch, Robert Harper, Jorg...
Abstract. The paper introduces a reinforcement learning-based methodology for performance improvement of Intelligent Controllers. The translation interfaces of a 3-level Hierarchic...
Today, the development of a VR application is still a long and difficult task. You need to be skilled in Virtual Reality (VR) technology to be able to develop a Virtual World. The...
Wesley Bille, Olga De Troyer, Frederic Kleinermann...
A quantum device simulating human decision making process is introduced. It consists of quantum recurrent nets generating stochastic processes which represent the motor dynamics, ...