# Schedule
This is a directed study course in Computer Science. In Spring 2027, the group will investigate Markov games with large number of players and in particular, the emergence of specialization in asymmetric Markov perfect equilibria, for example, when training drone swarms with hetergeneity, when and how will specialization appear.
| Week |
Date |
Topic |
Notes |
| 1 |
- |
Markov Games |
W1 |
| 2 |
- |
Markov Perfect Equilibrium |
W2 |
| 3 |
- |
Partial Observability |
W3 |
| 4 |
- |
Bayesian Games |
W4 |
| 5 |
- |
Deep Reinforcement Learning |
W5 |
| 6 |
- |
Policy Gradient Methods |
W6 |
| 7 |
- |
Mean Field Games |
W7 |
| 8 |
- |
Clustering and Visualization |
W8 |
| 9 |
- |
Project |
W9 |
| 10 |
- |
Project |
W10 |
| 11 |
- |
Project |
W11 |
| 12 |
- |
Project |
W12 |
| 13 |
- |
Project |
W13 |
| 14 |
- |
Project |
W14 |
| 15 |
- |
Project |
W15 |
Textbook (main):
📗 Multi-Agent Reinforcement Learning:
Link.
📗 Algorithmic Game Theory:
Link.
Notes from previous semesters:
📗 Information Design:
Link 📗 Reinforcement Learning for Robotics:
Link 📗 Continuous Action Games:
Link 📗 Partial Observability:
Link 📗 Multi-agent Deep Learning:
Link 📗 Single-agent Deep Learning:
Link 📗 Multi-agent Reinforcement Learning:
Link