|Phone:||+( 31) 152 785 117|
The Machine learning group (MAL) builds on the expertise of its members in nature-inspired algorithms, control, system identification computational intelligence, data analysis and data mining. In evolutionary computation, our interests are in the design of effective and efficient algorithms for solving real-parameter black-box optimization problems and in applications of evolutionary algorithms to hard combinatorial optimization problems, both single-objective and multi-objective ones, such as vehicle routing, robot gait pattern generation, bioinformatics, portfolio optimization, etc. We also have long-term experience in the field of reinforcement learning, adaptive control, nonlinear state estimation and robotics. Currently, our group works on a project entitled “Symbolic Regression for Reinforcement Learning in Continuous Spaces”, which is funded by the Czech Science Foundation GACR. The goal of the project is to automate the search process for the value function and policy approximators. The result will be a new class of RL methods suitable for continuous, high-dimensional state and action spaces.
Responsible: Robert Babuška