# Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking

arXiv: https://arxiv.org/abs/2603.06607 · HTML: https://mlsanity.com/paper/2603.06607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks](https://mlsanity.com/paper/2006.07869/) (2020)
- [A Review of Cooperative Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1908.03963/) (2019)
- [Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges](https://mlsanity.com/paper/1907.09059/) (2019)
- [AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2105.04196/) (2021)
- [Graph Neural Networks and Deep Reinforcement Learning Based Resource Allocation for V2X Communications](https://mlsanity.com/paper/2407.06518/) (2024)
- [Semantic-Aware Resource Allocation Based on Deep Reinforcement Learning for 5G-V2X HetNets](https://mlsanity.com/paper/2406.07996/) (2024)
- [Multi-user Resource Control with Deep Reinforcement Learning in IoT Edge Computing](https://mlsanity.com/paper/1906.07860/) (2019)
- [Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2411.04672/) (2024)
- [Multi-Timescale Control and Communications with Deep Reinforcement Learning -- Part II: Control-Aware Radio Resource Allocation](https://mlsanity.com/paper/2311.11280/) (2023)
- [Federated Reinforcement Learning for Resource Allocation in V2X Networks](https://mlsanity.com/paper/2310.09858/) (2023)

## Abstract (arXiv)

Radio resource allocation (RRA) is a critical function in cellular vehicle-to-everything (C-V2X) networks, where vehicles must share limited wireless resources to support safety-critical communications. Multi-agent reinforcement learning (MARL) has emerged as a promising approach for this problem. However, key MARL challenges, including non-stationarity, coordination difficulty, large action space, partial observability, and limited robustness and generalization, are often intertwined, making it difficult to assess their individual impact on performance in vehicular environments. Moreover, existing studies primarily focus on developing new algorithms, while systematic benchmarking and comparative analyses remain limited. To address this gap, we formulate C-V2X RRA as a hierarchy of multi-agent interference games that progressively introduce key MARL challenges. Based on this framework, we develop a suite of benchmark learning tasks and construct training and testing datasets from SUMO-generated highway traces with diverse vehicular topologies and interference conditions. Using the proposed benchmark, we evaluate representative MARL algorithms spanning value-based, actor-critic, Independent Learning (IL), and Centralized Training with Decentralized Execution (CTDE) paradigms. The results identify robustness and generalization across diverse vehicular topologies as the dominant challenge among those considered in this work, reducing average normalized return by up to 59 percentage points, and show that, on the most challenging task, the best actor-critic method outperforms the best value-based method by 42%. By revealing the relative strengths and limitations of different MARL paradigms and open-sourcing the code, datasets, and benchmark suite, this work provides a systematic and reproducible foundation for evaluating and advancing MARL algorithms in vehicular networks.