Efficient Teammate Adaptation with Language-assisted Progressive Intention Alignment

Enabling agents to collaborate effectively with diverse and previously unseen teammates remains a core challenge in multi-agent reinforcement learning (MARL), particularly in open environments. While existing research has made significant strides in adapting to diverse teammate behaviors under a fixed shared reward, the challenge of collaborating with partners who pursue distinct and unobservedpersonalrewards(intentions)remainsunexplored. Moreover, existing teammate modeling relies primarily on low-level behavioral cues while overlooking high-level semantic priors (e. g. , language descriptions), resulting in inefficient intention identification. We introduce TALP, a Bayesian framework for intention-aware teammate adaptation. At deployment, it leverages language priors and interaction history to perform unbiased intention inference, enabling targeted cooperation within a single episode. Experiments demonstrate that TALP accurately infers teammate intentions and significantly boosts collaborative efficiency.

Authors

• Zhichao Wu Nanjing University
• Ruiqi Xue Nanjing University
• Yichen Li Nanjing University
• Cong Guan Nanjing University
• Jingwen Yang Tencent
• Lei Yuan Nanjing University
• Yang Yu Nanjing University

Keywords

• Multi-agent Reinforcement Learning
• Coordination and Cooperation
• Intention Alignment