Kalyan Varma Nadimpalli

Post Baccalaureate Fellow

Hierarchical Reinforcement Learning

I have completed an integrated Masters at IIIT, Bangalore. Currently I am interested in making the RL framework more tractable, in particular I’m interested in temporal abstraction. How can we discover temporally extended skills that will make planning easier?

Towards this I am exploring option discovery frameworks under the supervision of Prof. Balaraman Ravindran.