ECE 49595 - Introduction to Reinforcement Learning
Note:
Students are discouraged from taking both this course and ECE 59500 Reinforcement Learning: Theory and Algorithms due to the amount of overlap between the courses. Should a student take both, the second will count as a Complementary Selective.
Course Details
Lecture Hours: 3 Credits: 3
Counts as:
- EE Elective
- EE - Automatic Control Concentration
- EE - Artificial Intelligence and Machine Learning Concentration
- CMPE Selective - Special Content
- CMPE - Artificial Intelligence and Machine Learning Concentration
Experimental Course Offered:
Spring 2024, Spring 2025, Spring 2026
Campus/Online:
On-campus only
Requisites:
ECE 30200 and ECE 20875 and MA 26100 and [MA 26200 or MA 26500]
Requisites by Topic:
Undergraduate understanding of probability, programming in Python, multivariate calculus and linear algebra
Catalog Description:
This course introduces the foundations of reinforcement learning, an area of machine learning closely tied to optimal control that studies sequential decision-making under uncertainty. It provides a broad overview of different interrelated problems and algorithmic solutions in reinforcement learning and its extensions, such as deep learning-driven methods.
Required Text(s):
None.
Recommended Text(s):
- Dynamic Programming and Optimal Control , 4th Edition , Dimitri P. Bertsekas , Athena Scientific , 2011 , ISBN No. 13: 978-1886529441
- Foundations of Deep Reinforcement Learning , 1st Edition , Laura Graesser and Wah Loon Keng , Addison-Wesley Professional , 2019 , ISBN No. 13: 978-0135172384
- Reinforcement Learning: An Introduction , 2nd Edition , Richard S. Stton and Andrew G. Barto , MIT Press , 2018 , ISBN No. 13: 978-0262039246
Learning Outcomes:
- an understanding of different problem formulations for reinforcement learning. [1]
- an ability to apply various algorithmic solutions to a wide range of sequential decisionmaking problems. [1]
- an ability to simulate data-driven sequential decision-making algorithms and analyze their performance. [6]
Lecture Outline:
| Week(s) | Lecture Topics |
|---|---|
| 1-5 | Fundamentals: Markov Decision Processes, Dynamic Programming, Value Iteration and Policy Iteration, Model-Free Methods, and On-Policy and Off-Policy Methods |
| 6-14 | Learning problems and Algorithms: Background on deep learning, deep reinforcement learning methods, policy gradient methods, actor-critic methods, model-based reinforcement learning, models with continuous states and actions, reinforcement learning with partial observability, multi-agent reinforcement learning, imitation learning and reinforcement learning from human feedback. |
| 15 | Case Studies |
Assessment Method:
Exams, quizzes and homework