This paper proposes a coordinated few-step flow method for offline multi-agent decision making, aiming to preserve inter-agent coordination without the usual multi-step sampling cost. It is most relevant to researchers working on efficient generative policies for MARL.
arXiv:2605.01457v1 Announce Type: new Abstract: Generative models have emerged as a major paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step accelerations either distill a joint teacher into independent students or apply averaged velocities independently per agent, suggesting that few-step inference requires sacrificing inter-agent coordination. We show this trade-off is not necessary: single-pass…