AI in Education
Description
This is a reading course where we will provide initial material, and students will have the opportunity to choose and develop topics further based on their interests. A core component of the course involves students presenting several papers each week.
WeChat Group
Click the image to view full size
Proposed Time
- To be discussed in the class.
Assessment Mechanism
- Participation in class discussions.
- Quality of weekly presentations. Click here for some potential choice of topics and papers.
- A final report on a mutually agreed topic.
General Research Directions and Key Research Areas:
- Latent-State Modeling and Inference
- Adaptive Pedagogical Control
- Optimization of Scarce Resources
- Multi-Agent and Game-Theoretic Interaction
- Assessment, Verification, and Content Generation
- Ethical and Human-Centered Considerations
Click here for more detailed information.
Weekly Presentation Slides
Background Reading Materials
Reinforcement Learning
Video Series
- Steve Brunton's "Control Bootcamp" series on YouTube.
Link to the playlist - Steve Brunton's "Reinforcement Learning" series on YouTube.
Link to the playlist
Textbook
- "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto.
- Chap 3: Basic MDP formulation.
- Chap 4: DP formulation.
- Chap 6: Classic RL algorithms (TD learning, Q learning).
- Chap 13: Policy gradient method.
Survey Paper
- Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges
Link to the paper
Game Theory
Video Series
- Game theory vidoe series on YouTube.
Link to the playlist
Offering Time
- 2025 Fall
Instructor
Costas Courcoubetis
Presidential Chair Professor
Presidential Chair Professor of the Chinese University of Hong Kong, Shenzhen.