combinatorial multi-armed bandits

Reinforcement Learning and Optimization in Large Action Spaces under Limited Feedback

Fares Fourati, Ph.D. Student, Electrical and Computer Engineering

Apr 29, 15:00 - 16:45

B2 R5209

Reinforcement Learning machine learning combinatorial multi-armed bandits large action spaces limited feedback efficient exploration submodular optimization black-box optimization global optimization

This dissertation develops theoretical foundations and scalable algorithms for reinforcement learning and optimization in large decision spaces under limited feedback.

Fares Fourati

Ph.D. Student, Electrical and Computer Engineering

machine learning Deep learning Reinforcement Learning artificial intelligence combinatorial multi-armed bandits intelligent systems black-box optimization

Fares Fourati is a Ph.D. student at the King Abdullah University of Science and Technology (KAUST), under the supervision of Professor Mohamed-Slim Alouini.