COIN: Collaborative Interaction-Aware Multi-Agent Reinforcement Learning for Self-Driving Systems

• URL: http://arxiv.org/abs/2603.24931v1
• Date: Thu, 26 Mar 2026 01:48:25 GMT
• Title: COIN: Collaborative Interaction-Aware Multi-Agent Reinforcement Learning for Self-Driving Systems
• Abstract summary: We propose a novel collaborative(CO-) interaction-aware(-IN) MARL framework, named COIN.<n>COIN aims to jointly optimize the individual objectives (navigation) and the global objectives (collaboration) of agents.<n>COIN consistently outperforms other advanced baseline methods in both safety and efficiency across various system sizes.
• Score: 11.28367642438173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-Agent Self-Driving (MASD) systems provide an effective solution for coordinating autonomous vehicles to reduce congestion and enhance both safety and operational efficiency in future intelligent transportation systems. Multi-Agent Reinforcement Learning (MARL) has emerged as a promising approach for developing advanced end-to-end MASD systems. However, achieving efficient and safe collaboration in dynamic MASD systems remains a significant challenge in dense scenarios with complex agent interactions. To address this challenge, we propose a novel collaborative(CO-) interaction-aware(-IN) MARL framework, named COIN. Specifically, we develop a new counterfactual individual-global twin delayed deep deterministic policy gradient (CIG-TD3) algorithm, crafted in a "centralized training, decentralized execution" (CTDE) manner, which aims to jointly optimize the individual objectives (navigation) and the global objectives (collaboration) of agents. We further introduce a dual-level interaction-aware centralized critic architecture that captures both local pairwise interactions and global system-level dependencies, enabling more accurate global value estimation and improved credit assignment for collaborative policy learning. We conduct extensive simulation experiments in dense urban traffic environments, which demonstrate that COIN consistently outperforms other advanced baseline methods in both safety and efficiency across various system sizes. These results highlight its superiority in complex and dynamic MASD scenarios, as further validated through real-world robot demonstrations. Supplementary videos are available at https://marmotlab.github.io/COIN/

Related papers

• IMAGINE: Intelligent Multi-Agent Godot-based Indoor Networked Exploration [0.0]
  This paper implements Multi-Agent Reinforcement Learning (MARL) to address challenges in a 2D indoor environment.<n>Policy training aims to achieve emergent collaborative behaviours and decision-making under uncertainty.
  arXiv  Detail & Related papers  (2026-02-02T22:08:41Z)
• Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge [170.47383225329915]
  Multi-agent system frameworks are becoming essential for achieving scalable, efficient, and collaborative solutions.<n>This shift is fueled by three primary factors: increasing agent capabilities, enhancing system efficiency through task delegation, and enabling advanced human-agent interactions.<n>We propose the Multi-Agent Robotic System (MARS) Challenge, held at the NeurIPS 2025 Workshop on SpaVLE.
  arXiv  Detail & Related papers  (2026-01-26T17:56:19Z)
• Multiagent Reinforcement Learning with Neighbor Action Estimation [5.226225544973531]
  This paper proposes an enhanced multiagent reinforcement learning framework that employs action estimation neural networks to infer agent behaviors.<n>At the engineering application level, this framework has been implemented and validated in dual-arm robotic manipulation tasks.
  arXiv  Detail & Related papers  (2026-01-08T02:26:57Z)
• Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams [0.6676697660506798]
  We propose a decentralized Multi-Agent Reinforcement Learning (MARL) framework that enables vehicles, acting as agents, to communicate selectively based on local goals and observations.<n>This goal-aware communication strategy allows agents to share only relevant information, enhancing collaboration while respecting visibility limitations.<n>Results show that our method significantly improves task success rates and reduces time-to-goal compared to non-cooperative baselines.
  arXiv  Detail & Related papers  (2025-11-15T02:11:31Z)
• Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance [1.1718316049475228]
  Multi-Agent Systems (MAS) excel at accomplishing complex objectives through the collaborative efforts of individual agents.<n>In this paper, we introduce a novel framework that aims to overcome the challenge of designing an effective reward function.<n>By giving large language models (LLMs) on the prioritization of tasks, our framework generates reward functions that can be dynamically adjusted online.
  arXiv  Detail & Related papers  (2025-07-22T09:26:00Z)
• SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving [51.47621083057114]
  SOLVE is an innovative framework that synergizes Vision-Language Models with end-to-end (E2E) models to enhance autonomous vehicle planning.<n>Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components.
  arXiv  Detail & Related papers  (2025-05-22T15:44:30Z)
• CoMAL: Collaborative Multi-Agent Large Language Models for Mixed-Autonomy Traffic [11.682456863110767]
  CoMAL is a framework designed to address the mixed-autonomy traffic problem by collaboration among autonomous vehicles to optimize traffic flow.<n>CoMAL is built upon large language models, operating in an interactive traffic simulation environment.
  arXiv  Detail & Related papers  (2024-10-18T10:53:44Z)
• Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning [57.652899266553035]
  Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server. We propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
  arXiv  Detail & Related papers  (2024-03-11T09:21:11Z)
• Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning [52.7873574425376]
  Cooperative multi-agent reinforcement learning (MARL) faces significant scalability issues due to state and action spaces that are exponentially large in the number of agents. We propose a novel, value-based multi-agent algorithm called LOMAQ, which incorporates local rewards in the Training Decentralized Execution paradigm.
  arXiv  Detail & Related papers  (2021-09-22T10:08:15Z)
• F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning [110.35516334788687]
  Decentralized multi-agent reinforcement learning algorithms are sometimes unpractical in complicated applications. We propose a flexible fully decentralized actor-critic MARL framework, which can handle large-scale general cooperative multi-agent setting. Our framework can achieve scalability and stability for large-scale environment and reduce information transmission.
  arXiv  Detail & Related papers  (2020-04-17T14:56:29Z)
• Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning [55.20040781688844]
  QMIX is a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. We propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-19T16:51:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.