activity
20162021
most citedScalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

23 citations · 36 across the 7 of their papers we have counts for

collaborators
Showing math.OCShow all

15 papers · 1 filter

math.OC20211 cited

Optimal Distributed Energy Resource Coordination: A Decomposition Method Based on Distribution Locational Marginal Costs

Panagiotis Andrianesis, Michael Caramanis, Na Li

In this paper, we consider the day-ahead operational planning problem of a radial distribution network hosting Distributed Energy Resources (DERs) including rooftop solar and stora…

math.OC20212 cited

On the Regret Analysis of Online LQR Control with Predictions

Runyu Zhang, Yingying Li, Na Li

In this paper, we study the dynamic regret of online linear quadratic regulator (LQR) control with time-varying cost functions and disturbances. We consider the case where a finite…

math.OC20201 cited

Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems

Yujie Tang, Zhaolin Ren, Na Li

We study a class of cooperative multi-agent optimization problems, where each agent is associated with a local action vector and a local cost, and the goal is to cooperatively find…

math.OC202023 cited

Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

Guannan Qu, Yiheng Lin, Adam Wierman +1

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exp…

math.OC2019

Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure

Guannan Qu, Na Li

This paper considers a multi-agent Markov Decision Process (MDP), where there are agents and each agent is associated with a state and action taking values from…

math.OC2019

Robust Hybrid Zero-Order Optimization Algorithms with Acceleration via Averaging in Time

Jorge I. Poveda, Na Li

We study novel robust zero-order algorithms with acceleration for the solution of real-time optimization problems. In particular, we propose a family of extremum seeking dynamics t…