Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality
This work addresses the problem of accelerating multi-agent planning for researchers and practitioners, but it is incremental as it builds on existing heuristics with a learning-based component.
The paper tackles the scalability issue of Conflict-Based Search for multi-agent path finding by proposing a Graph Transformer heuristic, which is provably complete and bounded-suboptimal, achieving better performance than state-of-the-art methods in experiments on dense graphs.
Conflict-Based Search is one of the most popular methods for multi-agent path finding. Though it is complete and optimal, it does not scale well. Recent works have been proposed to accelerate it by introducing various heuristics. However, whether these heuristics can apply to non-grid-based problem settings while maintaining their effectiveness remains an open question. In this work, we find that the answer is prone to be no. To this end, we propose a learning-based component, i.e., the Graph Transformer, as a heuristic function to accelerate the planning. The proposed method is provably complete and bounded-suboptimal with any desired factor. We conduct extensive experiments on two environments with dense graphs. Results show that the proposed Graph Transformer can be trained in problem instances with relatively few agents and generalizes well to a larger number of agents, while achieving better performance than state-of-the-art methods.