P. R. Kumar

Preserving Privacy and Fidelity via Ehrhart Theory

2018

We consider the problem of designing a database sanitization mechanism (DSM) that minimizes, in the expected sense, the L1-distortion between the histograms of original and sanitized databases, while being θ-differentially private (DP). The expected L1-distortion …

Fast Global Convergence of Policy Optimization for Constrained MDPs.

2021 · arXiv (Cornell University)

We address the issue of safety in reinforcement learning. We pose the problem in a discounted infinite-horizon constrained Markov decision process framework. Existing results have shown that gradient-based methods are able to achieve an $\mathcal{O}(1/\sqrt{T})$ …

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

2023 · arXiv (Cornell University)

We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focus …