Courses - Fall 2025
CMSC389L
Special Topics in Computer Science; Reinforcement Learning
Credits:
1
Grad Meth:
Reg
Minimum grade of C- in CMSC216, CMSC250, CMSC320; MATH241, 1 course witha minimum grade of C- from (MATH240, MATH461); and permission of CMNS-Computer Science department.
This course provides a comprehensive introduction to reinforcement learning. We begin with a review of key concepts in machine learning and planning, such as gradient descent and neural networks. We then explore core reinforcement learning algorithms-including value-based, policy-gradient, and actor-critic methods-along with essential tools like TensorFlow and Gymnasium. The course focuses on applications in robotics and autonomous systems, finance, and games.
This course provides a comprehensive introduction to reinforcement learning. We begin with a review of key concepts in machine learning and planning, such as gradient descent and neural networks. We then explore core reinforcement learning algorithms-including value-based, policy-gradient, and actor-critic methods-along with essential tools like TensorFlow and Gymnasium. The course focuses on applications in robotics and autonomous systems, finance, and games.
A student-led course through Student-Initiated Courses (STICs) @ UMD: http://stics.umd.edu/ Please click here for more information.
Flagship Institution of the University System of Maryland
University of Maryland, College Park, MD 20742, USA
/
Phone:
301.405.1000
Copyright
© 2025 University of Maryland
/
Privacy /
Web Accessibility
Contact us
with comments, questions and feedback
/