SRMT: Shared Memory for Multi-agent Lifelong Pathfinding

Understand

Coordination in decentralized multi-agent reinforcement learning (MARL) necessitates that agents share information about their behavior and intentions.

• Existing approaches rely on communication protocols with domain or resource constraints or centralized training that poorly scales to large agent populations.
• We introduce the Shared Recurrent Memory Transformer (SRMT), which enables coordination through unconstrained communication.
• SRMT provides a global memory workspace where agents broadcast their learned working memory states and query others' memory representations to exchange information and coordinate while maintaining decentralized training and execution.