Project Description

In this project, we will consider fundamental analysis of reinforcement learning. Further, the concepts of reinforcement learning and bandits will be applied for problems in networking, transportation, and manufacturing. 

Start Date

05/01/2019

Postdoc Qualifications

PhD in Electrical Engineering, Computer Science, Statistics, or related areas.  

Co-advisors

Vaneet Aggarwal, IE, https://engineering.purdue.edu/CLANLabs

Shweta Singh, ABE, https://sites.google.com/site/shwetasinghlab/ 

References

1. C. Pike-Burke, S. Agrawal, S. Grunewalder, C. Szepesvari, Bandits with Delayed, Aggregated Anonymous Feedback, ICML 2018.

2. S. Agrawal, R. Jia, "Optimistic posterior sampling for reinforcement learning: worst-case regret bounds". NIPS 2017

3. Yu, Zhe, Yunjian Xu, and Lang Tong. "Deadline scheduling as restless bandits." IEEE Transactions on Automatic Control (2018).

4. Maillard, Odalric-Ambrym, and Shie Mannor. "Latent Bandits." International Conference on Machine Learning. 2014.