CSC 8980
 Deep Reinforcement Learning


Course Schedule

(Tentative schedule for the course and deviations may be necessary as the course progresses.)

Date Topic Notes Reading (Textbook or Other Materials)
Jan. 10 Introduction RL: Chapter 1, Nature, Basic calculus refresher
Jan. 12 Machine Learning Basics Machine learning math essentials
Jan. 17 Sequential Decision Making
RL: Chapter 1
Jan. 19 Markov Decision Processes (MDP)
Project Details
RL: Chapter 3
Jan. 24
MDP Bellman Equations
RL: Chapter 3
Jan. 31
Policy Iteration, Value Iteration
RL: Chapter 4
Feb. 2
Tutorial on Numpy and PyTorch
Feb. 7
Model-free Prediction: MC vs. TD
RL: Chapter 5,6,7
Feb. 9 Model-free Control: SARSA, Q-Learning RL: Chapter 6
Feb. 14 Function Approximation: Linear Classifiers RL: Chapter 9
Feb. 16 Computational Graphs, Backpropagation DL: Chapter 8
Feb. 21 Neural Networks, MLP
Feb. 23 Convolutional Neural Networks AlexNet, ResNet
Feb. 28 Training Neural Networks
Mar. 2 Recurrent Nerual Networks, LSTM
Mar. 7 Transformer Attention is all you need, tutorial
Mar. 9 Deep Q Network (DQN)
Mar. 21 Policy Gradient
Mar. 23 Actor-Critic Homework4
Mar. 28 Sparse Reward Faulty reward, HER
Mar. 30 Imitation Learning IRL
Apr. 4 Model-based RL
Apr. 6 AlphaGo, AlphaGo Zero Notes on final exam and presentation Nature
Apr. 11 Review(office hours)
Apr. 13 Final Exam
Apr. 18 Presentation
Apr. 20 Presentation
Apr. 25 Presentation
Apr. 28 Project Report Due (by 11:59 pm)

 

 

back to course page