3 papers
cs.LG2026
Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes
Asha Barua, Sajad Khodadadian
Natural Policy Gradient (NPG) is a well-established Reinforcement Learning algorithm that underlies widely used methods such as Trust Region Policy Optimization and Proximal Policy…
math.PR2025
Quantization for the mixtures of overlap probability distributions
Asha Barua, Angelina Chavera, Ivan Djordjevic +4
Optimal quantization for mixed distributions has emerged as a compelling area of study. In this work, we have focused on a mixed distribution formed from two uniform distributions…
math.PR2025
Quantization for the mixtures of uniform distributions on connected and disconnected line segments
Asha Barua, Gustavo Fernandez, Ashley Gomez +2
In this paper, we have studied various mixed distributions generated by two uniform distributions: first, where the supports are two connected line segments, and second, where the…