DEEP Reinforcement Learning
Class overview
Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research is at the forefront of machine learning. Deep RL is able to solve a wide range of complex decision-making tasks, opening up new opportunities in domains such as healthcare, robotics, smart grids, finance, and many more. This class will cover recent advances in deep RL, including imitation learning, Policy Gradients, Deep Q-learning, Actor-Critic algorithms, and model-based RL. The course will be a combination of lectures, student presentations, and projects.
Lecturer: Qi (Rose) Yu (roseyu@ucsd.edu)
TA: Kwonjoon Lee (kwl042@eng.ucsd.edu); OH - 5-6 pm, Wed @ EBU3B B215
Time: 6:30 pm -7:50 pm PT Mon, Wed; OH - 5-6 pm, Mon @CSE 3208
Location: Revelle North Outdoor Space
Piazza: piazza.com/ucsd/fall2021/cse2915
Syllabus
Lectures
Class Assessment
30 % homework (10% x 3)
50 % project
5 % proposal
15 % milestone report
20 % final report
10 % final presentation
15 % paper discussion
5 % lecture scribe
Resources
Reading Materials
FAQ
Q: What are the pre-requisites?
CSE 150b (or equivalent) and CSE 151a (or equivalent) or CSE 250a
CSE 151b (or equivalent)
Proficiency in Python.
Q: Can first year undergraduates take this course?
Restricted to students with sophomore, junior, or senior standing within the CS25, CS26, CS27, CS28, EC26, and DS25 majors.
All other students will be allowed as space permits.
About me
My Chinese name is Qi Yu. That is also the instructor name in the registrar's office. I publish under the name Rose Yu. You can learn more about my research at my personal website.