在竞争性多智能体环境中学习沟通与协作，以清理大型塑料垃圾污染海洋（英文版）

英文标题：Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics中文摘要：本文提出一种基于图神经网络的通信机制，用于多智能体强化学习 (MARL) 环境中的宏塑料收集。实验表明这种通信机制能够有效地提高多智能体的协作性能，同时保持良好的个体表现。英文摘要：Finding a balance between collaboration and competition is crucial forartificial agents in many real-world applications. We investigate this using aMulti-Agent Reinforcement Learning (MARL) setup on the back of a high-impactproblem. The accumulation and yearly growth of plastic in the