| Relevance of Course Objectives and Core Learning Outcomes(%) |
Teaching and Assessment Methods for Course Objectives |
| Course Objectives |
Competency Indicators |
Ratio(%) |
Teaching Methods |
Assessment Methods |
(1) Learn the mathematical & algorithmic foundations of Reinforcement Learning
(2) Explore & understand advanced approaches to RL (e.g., Deep Q-learning, Actor-Critic, Policy Gradient)
(3) Use Python to solve hands-on RL programming problems
|
|
|
|
| Oral Presentation |
| Assignment |
|
| Course Content and Homework/Schedule/Tests Schedule |
| Week |
Course Content |
| Week 1 |
Class Introduction & Reinforcement Learning Overview |
| Week 2 |
Markov Decision Processes (MDPs) |
| Week 3 |
Dynamic Programming - Prediction & Control |
| Week 4 |
Monte Carlo Methods |
| Week 5 |
Temporal Difference Learning |
| Week 6 |
n-Step Temporal Difference Methods |
| Week 7 |
Supervised learning, Neural networks & PyTorch |
| Week 8 |
On-policy Prediction with Function Approximation |
| Week 9 |
Control with Value Function Approximation |
| Week 10 |
Policy Gradient Methods |
| Week 11 |
Actor-Critic Methods |
| Week 12 |
Evolutionary Algorithms |
| Week 13 |
Rollout Algorithms, Off-policy AC, Multiagent |
| Week 14 |
Class Review |
| Week 15 |
Final project presentations |
| Week 16 |
Final project presentations (continued) |
| Week 17 |
Self-study |
| Week 18 |
Self-study |
|
| Evaluation |
| Homework 75%, Final Project 25% |
| Textbook & other References |
| Reinforcement Learning: An Introduction, 2nd Ed., R. Sutton & A. Barto (MIT Press, 2018) |
| Teaching Aids & Teacher's Website |
|
| Office Hours |
|
| Sustainable Development Goals, SDGs |
| include experience courses：N |
|