# Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control

arXiv: https://arxiv.org/abs/2308.02345 · HTML: https://mlsanity.com/paper/2308.02345/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2023.

## Built on by (most cited first, 9 of 9)

- [WcDT: World-centric Diffusion Transformer for Traffic Scene Generation](https://mlsanity.com/paper/2404.02082/) (2024)
- [Towards Interactive and Learnable Cooperative Driving Automation: a Large Language Model-Driven Decision-Making Framework](https://mlsanity.com/paper/2409.12812/) (2024)
- [CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Driving](https://mlsanity.com/paper/2503.08683/) (2025)
- [LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems](https://mlsanity.com/paper/2511.19368/) (2025)
- [Scalable spectral representations for multi-agent reinforcement learning in network MDPs](https://mlsanity.com/paper/2410.17221/) (2024)
- [Multi-Agent Reinforcement Learning with Communication-Constrained Priors](https://mlsanity.com/paper/2512.03528/) (2025)
- [A Communication-Efficient Decentralized Actor-Critic Algorithm](https://mlsanity.com/paper/2510.19199/) (2025)
- [Cooperative Multi-agent RL with Communication Constraints](https://mlsanity.com/paper/2601.12518/) (2026)
- [Reinforcement Learning with Distributed MPC for Fuel-Efficient Platoon Control with Discrete Gear Transitions](https://mlsanity.com/paper/2601.18294/) (2026)

## Abstract (arXiv)

Connected and autonomous vehicles (CAVs) promise next-gen transportation systems with enhanced safety, energy efficiency, and sustainability. One typical control strategy for CAVs is the so-called cooperative adaptive cruise control (CACC) where vehicles drive in platoons and cooperate to achieve safe and efficient transportation. In this study, we formulate CACC as a multi-agent reinforcement learning (MARL) problem. Diverging from existing MARL methods that use centralized training and decentralized execution which require not only a centralized communication mechanism but also dense inter-agent communication during training and online adaptation, we propose a fully decentralized MARL framework for enhanced efficiency and scalability. In addition, a quantization-based communication scheme is proposed to reduce the communication overhead without significantly degrading the control performance. This is achieved by employing randomized rounding numbers to quantize each piece of communicated information and only communicating non-zero components after quantization. Extensive experimentation in two distinct CACC settings reveals that the proposed MARL framework consistently achieves superior performance over several contemporary benchmarks in terms of both communication efficiency and control efficacy. In the appendix, we show that our proposed framework's applicability extends beyond CACC, showing promise for broader intelligent transportation systems with intricate action and state spaces.