English

Sequence Modeling for N-Agent Ad Hoc Teamwork

Multiagent Systems 2025-10-21 v3

Abstract

N-agent ad hoc teamwork (NAHT) is a newly introduced challenge in multi-agent reinforcement learning, where controlled subteams of varying sizes must dynamically collaborate with varying numbers and types of unknown teammates without pre-coordination. The existing learning algorithm (POAM) considers only independent learning for its flexibility in dealing with a changing number of agents. However, independent learning fails to fully capture the inter-agent dynamics essential for effective collaboration. Based on our observation that transformers deal effectively with sequences with varying lengths and have been shown to be highly effective for a variety of machine learning problems, this work introduces a centralized, transformer-based method for N-agent ad hoc teamwork. Our proposed approach incorporates historical observations and actions of all controlled agents, enabling optimal responses to diverse and unseen teammates in partially observable environments. Empirical evaluation on a StarCraft II task demonstrates that MAT-NAHT outperforms POAM, achieving superior sample efficiency and generalization, without auxiliary agent-modeling objectives.

Keywords

Cite

@article{arxiv.2506.05527,
  title  = {Sequence Modeling for N-Agent Ad Hoc Teamwork},
  author = {Caroline Wang and Di Yang Shi and Elad Liebman and Ishan Durugkar and Arrasy Rahman and Peter Stone},
  journal= {arXiv preprint arXiv:2506.05527},
  year   = {2025}
}

Comments

Presented at RLDM 2025

R2 v1 2026-07-01T03:02:32.877Z