Reidentify: Context-Aware Identity Generation for Contextual Multi-Agent Reinforcement Learning
Shandong University · National University of Defense Technology · Institute of automation, Chinese academy of sciences, Chinese Academy of Sciences · University of Bristol · SenseTime Research · Institute of Automation, Chinese Academy of Sciences · CAS · Huazhong Agricultural University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Generalizing multi-agent reinforcement learning (MARL) to accommodate variations in problem configurations remains a critical challenge in real-world applications, where even subtle differences in task setups can cause pre-trained policies to fail. To address this, we propose Context-Aware Identity Generation (CAID), a novel framework to enhance MARL performance under the Contextual MARL (CMARL) setting. CAID dynamically generates unique agent identities through the agent identity decoder built on a causal Transformer architecture. These identities provide contextualized representations that align corresponding agents across similar problem variants, facilitating policy reuse and improving sample efficiency. Furthermore, the action regulator in CAID incorporates these agent identities into the action-value space, enabling seamless adaptation to varying contexts. Extensive experiments on CMARL benchmarks demonstrate that CAID significantly outperforms existing approaches by enhancing both sample efficiency and generalization across diverse context variants.