About the Reinforcement Learning (RL) Division
The Reinforcement Learning (RL) division of the KDD Lab focuses on the formation and optimization of policies for autonomous agents. Research topics include decoupled value and policy gradient networks, reward induction, and discounting.
The division is currently directed jointly by Nasik Muhammad Nafi and Farrukh Ali (fall 2019-present). The inaugural division lead (fall 2018-summer 2019) was Dr. Vahid Behzadan, now an assistant professor at the University of New Haven and PI of the Secure and Assured Intelligent Learning (SAIL) Lab.
Project-specific information for the RL division can be found below: