Order Acceptance under Uncertainty: a Reinforcement Learning Approach

Beta is the largest research centre in the Netherlands in the field of operations management in technology-intensive environments. The mission of Beta is to carry out fundamental and applied research on the analysis, design and control of operational processes. PROEFSCHRIFT ter verkrijging van de graad van doctor aan de Universiteit Twente, op gezag van de rector magnificus, prof.dr. Acknowledgements Many people have contributed to this thesis in different ways. I thank Aart van Harten and Peter Schuur very much for giving me the posibility to work in this project, for the nice discussions we had on several topics that helped me to finish this thesis. Special thanks go to the team from computer science: Martijn van Otterlo, Marko Snoek and Mannes Pool; for introducing me on the field of Reinforcement Learning, for the many discussions we had of all kind and for the yearly team-lunch we had. Thanks to the BETA school for organizing the PhD activitiess. Thanks to Mark Ebben, Erwin Hans and Floris Olde Weghuis for the insights in order acceptance and for facilitating me their integrated/generic simulation environment. Thanks to Jorge Luis for his help with the implementation of the ANNs to work with in eM-Plant. Thanks to Prof. for participating in my graduation committee. This thesis has taken many years to come to an end, and I could not have gone through this period without the support of all the many wonderful people I have met here and there, at both sides of the ocean. From one side. First, my Dutch non-dutch family: Adriana and Andrei. From the other side. First my parents and brother, who have always been with me in a way, for all their support and their lifes as models of eternal study.