# 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.

# Grading Scheme


There will be weekly meetings to discuss the progress of the project, and a final project submission: a demo on your personal website and a report.





Last Updated: August 29, 2024 at 11:27 PM