The framework of centralized training with decentralized execution (CTDE) [8,28]isone ofthe popular frameworks for solving cooperative multi-agent tasks.

Real-world multi-agent scenarios often involve mixed motives, demanding altruistic agents capable of self-protection against potential exploitation.

SeqComm are guaranteed to improve monotonically and converge.

Current approaches to learning cooperative multi-agent behaviors assume relatively restrictive settings.

Team-Nash equilibrium (TNE) predicts the outcomes of such coordinated interactions.

MARL in real scenarios is still challenging due to the same safety and efficiency concerns in single-agent setting, then it is worth conducting investigation for offline RL in multi-agent setting.

Work done during an internship at Zoox 37th Conference on Neural Information Processing Systems (NeurIPS 2023).