# Schedule
This is a directed study course in Computer Science. In Fall 2024, the topic is multi-agent deep reinforcement learning. We will implement an autonomous driving simulation environment similar to
Link, and we will use multi-agent Q network algorithms to train the vehicles instead of genetic algorithms. We will compare the performance of centralized and decentralized training and execution.
Week |
Date |
Topic |
Notes |
1 |
- |
Markov Game |
W1 |
2 |
- |
Best Response Dynamics |
W2 |
3 |
- |
Nash Q |
W3 |
4 |
- |
Imitation Learning |
W4 |
5 |
- |
Deep Q Network |
W5 |
6 |
- |
Policy Gradient |
W6 |
7 |
- |
Project |
W7 |
8 |
- |
Project |
W8 |
9 |
- |
Project |
W9 |
10 |
- |
Project |
W10 |
11 |
- |
Project |
W11 |
12 |
- |
Project |
W12 |
13 |
- |
Project |
W13 |
14 |
- |
Project |
W14 |
15 |
- |
Project |
W15 |
Notes from previous semesters:
📗 Multi-agent discrete state:
Link
📗 Single-agent deep learning:
Link
Textbooks: (main) Multi-Agent Reinforcement Learning:
Link, Reinforcement Learning:
Link, Game Theory:
Link.