Debabrota Basu

Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities

2019 · arXiv (Cornell University)

We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves the optimal …

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

2022 · arXiv (Cornell University)

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL …

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits

2022 · arXiv (Cornell University)

We study the problem of multi-armed bandits with $ε$-global Differential Privacy (DP). First, we prove the minimax and problem-dependent regret lower bounds for stochastic and linear bandits that quantify the hardness of bandits with $ε$-global …