# Scalability Bottlenecks in Multi-Agent Reinforcement Learning Systems

arXiv: https://arxiv.org/abs/2302.05007 · HTML: https://mlsanity.com/paper/2302.05007/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2023.

## Built on by (most cited first, 6 of 6)

- [MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization](https://mlsanity.com/paper/2302.10418/) (2023)
- [SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems](https://mlsanity.com/paper/2405.03967/) (2024)
- [Intelligent Offloading in Vehicular Edge Computing: A Comprehensive Review of Deep Reinforcement Learning Approaches and Architectures](https://mlsanity.com/paper/2502.06963/) (2025)
- [Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication](https://mlsanity.com/paper/2505.00540/) (2025)
- [Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2603.15054/) (2026)
- [Rate-Aware Quantum-Inspired Trajectory Learning for Interference-Limited Multi-UAV Networks](https://mlsanity.com/paper/2606.25480/) (2026)

## Abstract (arXiv)

Multi-Agent Reinforcement Learning (MARL) is a promising area of research that can model and control multiple, autonomous decision-making agents. During online training, MARL algorithms involve performance-intensive computations such as exploration and exploitation phases originating from large observation-action space belonging to multiple agents. In this article, we seek to characterize the scalability bottlenecks in several popular classes of MARL algorithms during their training phases. Our experimental results reveal new insights into the key modules of MARL algorithms that limit the scalability, and outline potential strategies that may help address these performance issues.