papers

Publications (13)

cs.LG2024

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization

Uri Gadot, Esther Derman, Navdeep Kumar +3

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most ad…

cs.LG2024

On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes

Navdeep Kumar, Yashaswini Murthy, Itai Shufaro +3

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we…

cs.AI2022

Efficient Policy Iteration for Robust Markov Decision Processes via Regularization

Navdeep Kumar, Kfir Levy, Kaixin Wang +1

Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for…

cs.AI2025

Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes

Navdeep Kumar, Adarsh Gupta, Maxence Mohamed Elfatihi +3

We study robust Markov decision processes (RMDPs) with non-rectangular uncertainty sets, which capture interdependencies across states unlike traditional rectangular models. While…

cs.LG2024

Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel

Kaixin Wang, Uri Gadot, Navdeep Kumar +2

Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, current RMDP methods…

cs.LG2023

An Efficient Solution to s-Rectangular Robust Markov Decision Processes

Navdeep Kumar, Kfir Levy, Kaixin Wang +1

We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs wh…