Dileep Kalathil

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 $\mathcal{O}(1/\sqrt{T})$ …

Dynamic Regret Analysis of Safe Distributed Online Optimization for Convex and Non-convex Problems

2023 · arXiv (Cornell University)

This paper addresses safe distributed online optimization over an unknown set of linear safety constraints. A network of agents aims at jointly minimizing a global, time-varying function, which is only partially observable to each individual …

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 …