dibs

COM SCI 260R: Reinforcement Learning

Lecture, four hours; discussion, two hours; outside study, six hours. Fundamentals and advanced topics of reinforcement learning (RL), computational learning approach where agent tries to maximize total amount of reward it receives while interacting with complex and uncertain environments. Includes introduction of Markov decision processes, model-free RL and model-based RL methods, policy optimization, RL distributed system design, as well as case studies of RL in game playing such as AlphaGo, traffic simulation, autonomous driving, and other machine autonomy applications. Advanced topics of RL such as multi-agent RL, human-in-loop method, and imitation learning. Letter grading.

4 units, graduate

Offered Fall quarters

Predicted GPA
3.43
A or A minus
52%
D, F or withdrew
0%
Sections
Sections not published yet.
By instructor
Fall 2023 to Winter 2025
All instructors
3.43 GPA
52% A
0% DFW
204 grades
ZHOU
3.43 GPA
52% A
0% DFW
204 grades
Prerequisites
Not read yet
Restrictions
Not read yet
Grading
Not read yet
Final exam
Final time not published

What past students say

Read from 2 reviews, all instructors

No professor is listed for this term yet, so these count the reviews of every professor who has taught it.

Recommend
1 advises against
Teaching
1 says unclear
Exams
1 says moderate, 1 hard
Curve
1 says not curved

Each figure counts the reviews that say so. Most reviews skip most topics.