CS680: Neural Networks and Reinforcement Learning (Spring '96)
- Meets: M/W/F 9:00--9:50 AM, 100 USC.
- Taught by: Chuck Anderson,
anderson@cs.colostate.edu
- Phone: 491-7491
- Office Hours: 225 USC, Tu/Th 1:00--4:00 PM
- Text: Hassoun, Fundamentals of Artificial Neural Networks
(MIT Press, 1995). We will also be using the draft of a book by
Sutton and Barto, and additional papers from the reinforcement
learning literature.
- The Computer Science Department
Student Information Sheet
Class Handouts and Resources
Course Description
Reinforcement learning refers to a broad class of learning
problems and algorithms that share the goal of optimizing the behavior
of an agent that can be modified with experience. An agent can
be a computer program, a control device in a feedback system, or an
autonomous robot. In class we will review the history of
reinforcement learning, starting from models of animal learning to
recent theoretical developments relating reinforcement learning and
dynamic programming methods. Neural networks will be discussed as one
way of learning the value and policy functions in dynamic programming
and reinforcement learning.
Students will be required critique and discuss current research
articles, implement and study neural net and reinforcement learning
algorithms, and complete a semester project either critiquing
existing theory or applying one of the discussed methods to a
practical problem.
Course Prerequisites
The prerequisite for this course is either CS540 or other experience
that provides a background on neural networks. Ideally, students will
have already implemented a neural network training algorithm. Check
with the instructor if you have any questions about your qualifications.
Last updated 1/19/96
anderson@cs.colostate.edu