Home
I am currently working with EE Dept. IIT Madras.
I work on problems of online auctions, restless multi-armed bandits, sequential decision problems, reinforcement learning. Its applications to communication systems, recommendation systems, intelligent transport systems and robotics.
Recent works:
Whittle Index Learning Algorithm for Restless Bandits with Constant Stepsizes ( joint work with V. Mittal and S. Prakash IIIT Allahabad)
Faster Q learning Algorithms for Restless Bandits (Joint work with Parvish Kakarapalli and Devendra Kayande IIIT Allahabad)
Multi-agents Q learning algorithms for restless bandits