I am very happy to supervise BSc / MSc student projects if they relate to my research interests.
For instance, I would be quite keen to supervise student projects focusing on applying AI techniques in the open source ‘SUMO’ traffic simulator (http://www.sumo.dlr.de/). Examples of such projects would be:
- Online Scheduling for Urban Traffic Light Control
- Reinforcement Learning for large-scale Urban Traffic Light Control
- Assessing the Impact of Improved Sensing for RL-Based Urban Traffic Light Control
Such projects would require good coding skills and a descent background in reinforcement learning or MDPs.
Another topic of interest would be:
- Game-theoretic Training of Adversarial Neural Networks
where we would investigate possible extensions of the GANGs formalism.
If you are interested, or have your own ideas for a project relating to reinforcement learning, multiagent learning, or adversarial learning, please contact me.