Author

Mudit Gaur

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity

This work proposes a hypergradient-based bilevel RL algorithm using the optimality of the Boltzmann policy for the entropy regularized discounted RL objective function and obtains an iteration complexity of $O(\epsilon^{-1})$ and state-of-the-art sample complexity of $\tilde{O}(\epsilon^{-2})$ under mild regularity conditions.

Naman Saxena, Mudit Gaur, Vaneet Aggarwal · arXiv.org · 0 citations