Scholar
Saket Tiwari
Google Scholar ID: dMIkIX8AAAAJ
PhD Candidate, Brown University
Citations & Impact
Citations
82
H-index
4
i10-index
3
Publications
10
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Provided one of the first successful applications of the theory of infinite width neural networks for continuous RL. Works on bridging the gap between theory and practice by explaining popular practical algorithms in meaningful theoretical settings.
Research Experience
- Research focuses on using theoretical tools from high-dimensional statistics, differential geometry, dynamical systems, and optimal control to answer how existing deep learning models utilize low-dimensional structure, how to exploit this structure to train better models, and what this structure is for RL and how to build agents that can utilize it.
Background
- 6th year PhD student at Brown University, focusing on Reinforcement Learning. Advised by Professor George Konidaris. Prior to Brown, obtained a master's degree from the University of Massachusetts, Amherst, and worked with Professor Phil Thomas. Graduated with a Bachelor of Technology in Computer Science from IIT Bombay. Research is focused on designing a geometric lens to understand and improve Deep Reinforcement Learning (RL).
Miscellany
- Believes that for true progress in Deep RL, theory should move towards practice and practice should move towards theory. Interests include using theoretical tools to help explain practical algorithms.
Co-authors