Latest Research Papers
2025-01-22
arXiv
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
The paper introduces SRMT, a method that enhances coordination in multi-agent systems by sharing and broadcasting working memories. SRMT outperforms various baselines in partially observable pathfinding tasks, particularly under sparse rewards. The results show that shared recurrent memory can improve cooperation in decentralized multi-agent settings.
Multi-agent reinforcement learning (MARL) demonstrates significant progress
in solving cooperative and competitive multi-agent problems in various
environments. One of the principal challenges in MARL is the need for explicit
prediction of the agents' behavior to achieve cooperation. To resolve this
issue, we propose the Shared Recurrent Memory Transformer (SRMT) which extends
memory transformers to multi-agent settings by pooling and globally
broadcasting individual working memories, enabling agents to exchange
information implicitly and coordinate their actions. We evaluate SRMT on the
Partially Observable Multi-Agent Pathfinding problem in a toy Bottleneck
navigation task that requires agents to pass through a narrow corridor and on a
POGEMA benchmark set of tasks. In the Bottleneck task, SRMT consistently
outperforms a variety of reinforcement learning baselines, especially under
sparse rewards, and generalizes effectively to longer corridors than those seen
during training. On POGEMA maps, including Mazes, Random, and MovingAI, SRMT is
competitive with recent MARL, hybrid, and planning-based algorithms. These
results suggest that incorporating shared recurrent memory into the
transformer-based architectures can enhance coordination in decentralized
multi-agent systems. The source code for training and evaluation is available
on GitHub: https://github.com/Aloriosa/srmt.