Print Email Facebook Twitter Towards Self-Learning Model-Based Evolutionary Algorithms Title Towards Self-Learning Model-Based Evolutionary Algorithms Author Meulman, Erik (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Bosman, Peter (mentor) Aardal, Karen (graduation committee) Bierkens, Joris (graduation committee) Degree granting institution Delft University of Technology Programme Applied Mathematics Date 2019-04-17 Abstract Model-based evolutionary algorithms (MBEAs) are praised for their broad applicability to black-box optimization problems. In practical applications however, they are mostly used to repeatedly optimize different instances of a single problem class, a setting in which specialized algorithms generally perform better. In this paper, we introduce the concept of a new type of MBEA that can automatically specialize its behavior to a given problem class using tabula rasa self-learning. For this, reinforcement learning (RL) is a naturally fitting paradigm. A proof-of-principle framework, called SL-ENDA, based on estimation of normal distribution algorithms in combination with reinforcement learning is defined. SL-ENDA uses an RL-agent to decide upon the next population mean while approaching the rest of the algorithm as the environment. A comparison of SL-ENDA to AMaLGaM and CMA-ES on unimodal noiseless functions shows mostly comparable performance and scalability to the broadly used and carefully manually crafted algorithms. This result, in combination with the inherent potential of self-learning model-based evolutionary algorithms with regard to specialization, opens the door to a new research direction with great potential impact on the field of model-based evolutionary algorithms. Subject Estimation of distribution algorithmsMachine LearningReinforcement Learning (RL)Black-box optimization To reference this document use: http://resolver.tudelft.nl/uuid:d7e9fdb1-7ced-43bb-b3ab-c4888fcc2482 Part of collection Student theses Document type master thesis Rights © 2019 Erik Meulman Files PDF Thesis_EAMeulman.pdf 656.92 KB Close viewer /islandora/object/uuid:d7e9fdb1-7ced-43bb-b3ab-c4888fcc2482/datastream/OBJ/view