Title:	Federated Reinforcement Learning
DNr:	NAISS 2025/22-1207
Project Type:	NAISS Small Compute
Principal Investigator:	Kakoli Majumder <kakoli.majumder@liu.se>
Affiliation:	Linköpings universitet
Duration:	2025-09-08 – 2026-10-01
Classification:	10212
Keywords:

Abstract

Federated reinforcement learning enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead and probabilistic risk constraints remain critical bottlenecks. These issues become more complex when the number of federated agents increases. We propose algorithms to solve such challenges.