← Search

Raghav Bongole

2 accepted papers

2025

Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality

ICASSP 2025accepted

We study agents acting in an unknown environment where the agent’s goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for all possible environments. To this end, we consider agents minimizing the maximum regret over different environment par…

Cited by 0SourceScholar