Abstract. This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double ...
A large class of systems of biological and technological relevance can be described as analog networks, that is, collections of dynamic devices interconnected by links of varying s...
Claudio Mattiussi, Daniel Marbach, Peter Dürr, Da...
Continuous Time Recurrent Neural Networks (CTRNNs) have previously been proposed as an enabling paradigm for evolving analog electrical circuits to serve as controllers for physica...
Problems such as the design of distributed controllers are characterized by modularity and symmetry. However, the symmetries useful for solving them are often difficult to determ...
Several different controller representations are compared on a non-trivial problem in simulated car racing, with respect to learning speed and final fitness. The controller rep...
Alexandros Agapitos, Julian Togelius, Simon M. Luc...