Master of Science in Computing Science - Reinforcement Learning (Thesis-based)

Reinforcement learning is a body of theory and algorithms for optimal decision making developed within the machine learning and operations research communities in the last twenty-five years, and which have separately become important in psychology and neuroscience. Reinforcement learning methods find useful approximate solutions to optimal-control problems that are too large or too ill-defined for classical methods such as dynamic programming. For example, reinforcement-learning methods have obtained the best-known solutions in such diverse automation applications as helicopter flying, elevator scheduling, playing backgammon, and resource-constrained scheduling.Reinforcement learning researchers at the University of Alberta seek to create new methods for reinforcement learning that remove some of the limitations on its widespread application and to develop reinforcement learning as a model of intelligence that could approach human abilities. These objectives are pursued through mathematics, through computational experiments, through applications in robotics, game-playing, and other areas, and through the development of computational models of natural learning processes.