Computer Science, Second Cycle, Reinforcement Learning, 6 Credits

Reinforcement learning is a machine learning method that learns to solve sequential decision making problems by trial and error. This means that a successful agent needs to make several optimal decisions to solve the problem and that the agent has to learn from experience by tying out different solutions. In this course we are providing the basis for understanding and using reinforcement learning algorithms for discrete and continuous environments, including deep reinforcement learning. We start with basic dynamic programming-based algorithms and also include state-of-the-art algorithms for continuous state and actions spaces.

This course is intended for working professionals.

ECTS Credits

6 Credits

Level of education

Second cycle, has only first-cycle course/s as entry requirements (A1N)

School

School of Science and Technology