The objective of this course is to learn to apply the technique of reinforcement learning to solve a variety of operational problems. After a successful completion of this course, students will be able to:
• relate reinforcement learning to (approximate) dynamic programming to solve MDPs;
• explain the role and purpose of neural networks in deep reinforcement learning;
• evaluate the diﬀerent design choices to set up a reinforcement learning algorithm;
• benchmark the performance of reinforcement learning to other (near-)optimal solutions;
• acknowledge the limitations of reinforcement learning;
• apply reinforcement learning as a general purpose technology to a problem of choice.
This course introduces the technique of reinforcement learning to optimize operations management prob-lems. It covers both theoretical foundations as well as implementation of reinforcement learning algorithms to practical problems. The focus will be on the eﬀective implementation to operations management prob-lems. All students are expected to design and implement a reinforcement learning algorithm for a problem of choice. Examples of reinforcement learning applications in the operations management and logistics ﬁeld are provided during the course. Coaching will be provided to assist the students in their assignment.
Opening session (on location):
• Reinforcement learning and its relation to (approximate) dynamic programming;
• The use of neural networks in reinforcement learning;
• Design choices to set up a reinforcement learning algorithm and the diﬀerent types of algorithms;
• Deﬁnition of the problem that will be covered during the assignment;
• How to get started?
Bi-weekly coaching sessions per squad (online).
Intermediate presentation to discuss the status (online).
Closing session (on location) with ﬁnal presentations and closure of the program.
A selected list of papers will be made available at the beginning of the course.