Multi-agent Reinforcement Learning: Theory and Applications
Interdisciplinary Areas: | Data and Engineering Applications, Autonomous and Connected Systems, Smart City, Infrastructure, Transportation |
---|
Project Description
In this project, we will study the aspects of MARL with different forms of objectives (e.g., fairness functions, multiple QoE/QoS tradeoffs) and constraints to prove mathematical guarantees. Further, the developed algorithms can be applied in a wide range of problems including communication networks, social networks, transportation networks, and games.
Start Date
Apr 2021
Postdoc Qualifications
The postdoc must have a PhD in Electrical Engineering, Computer Science, Mathematics, Statistics, or related areas.
Co-Advisors
Vaneet Aggarwal, vaneet@purdue.edu, School of IE and ECE, https://web.ics.purdue.edu/~vaneet
Chris Brinton, cgb@purdue.edu, School of ECE, http://www.cbrinton.net/
References
Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning
Multi-Agent Determinantal Q-Learning
arxiv.org/pdf/1909.02940.pdf
https://arxiv.org/pdf/2003.05555.pdf