Abstract. Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Qlearning is commonly applied to problems with d...
Chris Gaskett, David Wettergreen, Alexander Zelins...
The paper presents a new distributed metaheuristic algorithm in an optimal control problem related to the cooling process in the continuous casting of steel. The optimization task...
Peter Korosec, Jurij Silc, Bogdan Filipic, Erkki L...
Business process management (BPM) has emerged as a dominant technology in current enterprise systems and business solutions. However, the technology continues to face challenges i...