|
CSE 5820
Reinforcement Learning
|
(Tentative schedule for the course and deviations may be necessary as the course progresses.)
| Date |
Topic |
Notes |
Reading (Textbook or Other Materials) |
| Jan. 20 |
Introduction |
|
RL: Chapter 1, Nature, Basic calculus refresher |
| Jan. 22 |
Machine Learning Basics |
HW1 Q5 |
Machine learning math essentials |
| Jan. 29 |
Sequential Decision Making |
|
RL: Chapter 1 |
| Feb. 3 |
Markov Decision Processes (MDP) |
Project Details |
RL: Chapter 3 |
| Feb. 5 |
MDP Bellman Equations |
|
RL: Chapter 3 |
| Feb. 10 |
Policy Iteration, Value Iteration |
|
RL: Chapter 4 |
| Feb. 12 |
Model-free Prediction: MC vs. TD |
|
RL: Chapter 5,6,7 |
| Feb. 17 |
Model-free Control: SARSA, Q-Learning |
|
RL: Chapter 6 |
| Feb. 26 |
Function Approximation: Linear Classifiers |
|
RL: Chapter 9 |
| Mar. 3 |
Computational Graphs, Backpropagation |
|
DL: Chapter 8 |
| Mar. 5 |
Neural Networks, MLP |
|
|
| Mar. 10 |
Convolutional Neural Networks |
|
AlexNet, ResNet |
| Mar. 12 |
Recurrent Nerual Networks, LSTM |
|
|
| Mar. 24 |
Transformer |
|
Attention is all you need, tutorial |
| Mar. 26 |
Deep Q Network (DQN) |
|
|
| Mar. 31 |
Policy Gradient |
|
|
|