# 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 Decision Process |
W1 |
| 2 |
- |
Q Learning |
W2 |
| 3 |
- |
Normal Form Game |
W3 |
| 4 |
- |
Markov Game |
W4 |
| 5 |
- |
Nash Q |
W5 |
| 6 |
- |
Neural Networks |
W6 |
| 7 |
- |
Genetic Algorithm |
W7 |
| 8 |
- |
Deep Q Networks |
W8 |
| 9 |
- |
Multi Agent Q Networks |
W9 |
| 10 |
- |
Project |
W10 |
| 11 |
- |
Project |
W11 |
| 12 |
- |
Project |
W12 |
| 13 |
- |
Project |
W13 |
| 14 |
- |
Project |
W14 |
| 15 |
- |
Project |
W15 |
Textbooks: (main) Multi-Agent Reinforcement Learning:
Link, Reinforcement Learning:
Link, Game Theory:
Link.