Robust Reinforcement Learning Algorithms for Task Scheduling in Mobile Edge Computing Networks

Robust Reinforcement Learning Algorithms for Task Scheduling in Mobile Edge Computing Networks
Share this


Talk details

Title: Robust Reinforcement Learning Algorithms for Task Scheduling in Mobile Edge Computing Networks
Speaker: Dr. Arghyadip Roy, Assistant Professor at Indian Institute of Technology Guwahati, India
Date: 6th September 2025
Time: 3:00 PM (IST)

Abstract:

In an Internet of Things (IoT)-based network, tasks arriving at individual nodes can be processed in-device or at a Mobile Edge Computing (MEC) server. However, traditional Reinforcement Learning (RL) algorithms that can learn the optimal solution iteratively may not be robust under perturbations of system parameters, such as the task arrival rate. In this talk, we will discuss some of our recent work on robust RL algorithms for task allocation in an MEC-based IoT network. We will also present task allocation heuristics that can retain robustness towards distributional shift with a significant drop in computational complexity, albeit with loss in optimality.

Speaker’s bio

Dr. Arghyadip Roy is an assistant professor at the Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Guwahati, India. He was a postdoctoral research associate at the Coordinated Science Laboratory, UIUC, USA. Prior to that, he was a doctoral student in the Department of Electrical Engineering, Indian Institute of Technology Bombay. His research interests lie in reinforcement learning, Markov decision processes, and resource allocation in next-generation wireless networks (5G/6G).

Contact: