CAMAR: Continuous Actions Multi-Agent Routing

Авторы

Панов А. И. ,  Скрынник А. А.

Аннотация

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with challenging coordination and planning tasks. We introduce CAMAR, a new MARL benchmark designed explicitly for multi-agent pathfinding in environments with continuous actions. CAMAR supports cooperative and competitive interactions between agents and runs efficiently at up to 100,000 environment steps per second. We also propose a three-tier evaluation protocol to better track algorithmic progress and enable deeper analysis of performance. In addition, CAMAR allows the integration of classical planning methods such as RRT and RRT* into MARL pipelines. We use them as standalone baselines and combine RRT* with popular MARL algorithms to create hybrid approaches. We provide a suite of test scenarios and benchmarking tools to ensure reproducibility and fair comparison. Experiments show that CAMAR presents a challenging and realistic testbed for the MARL community.

Внешние ссылки

DOI: 10.1609/aaai.v40i35.40209

Скачать статью (PDF) на сайте AAAI (англ.): https://ojs.aaai.org/index.php/AAAI/article/view/40209

Скачать препринт статьи (PDF) на arXiv.org (англ.): https://arxiv.org/abs/2508.12845

РИНЦ: https://elibrary.ru/item.asp?id=91286488

ResearchGate: https://www.researchgate.net/publication/402626746_CAMAR_Continuous_Actions_Multi-Agent_Routing

Ссылка при цитировании

Pshenitsyn, A., Panov, A., & Skrynnik, A. (2026). CAMAR: Continuous Actions Multi-Agent Routing // Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29651–29659. https://doi.org/10.1609/aaai.v40i35.40209