Welcome! This is the codebase for assignments of our reinforcement learning (RL) course.
As this course is still polishing and growing, please feel free to open issues if you find anything wrong or confusing in codes or documents in this repository. We will respond to you as soon as possible. If you get stuck or mess up, take a look at the latest version of this repo may help, since somebody may already raise issues and bug is fixed by new commits.
We appreciate you for suggestion and contribution to improve this course!
Generally, the way you use this repo is:
- Check the latest release at the time the tutor announced a new assignment is coming.
- Read the assignment document, which is the
README.mdat each assignment directory. - Clone or fork or somewhat to get the codes or jupyter notebook at your computer.
- Fill the empty functions or slots or cells we left for you.
- Follow the instructions in code comments to check if everything work well.
- Follow the submission instruction in the assignments to submit your work in Blackboard. (If you are formal enrolled student.)
Beautiful code and comment make extra credits. Our aesthetic standard is PEP 8.
Assignment 0: Jupyter Notebook usage and assignment submission workflow
More assignments are comming soon!
2021-2022 1st term, IERG 5350: Reinforcement Learning. Department of Information Engineering, The Chinese University of Hong Kong. Course Instructor: Professor ZHOU Bolei. Assignment author: PENG Zhenghao.