Multi-agent path finding (MAPF) has been widely used to solve large-scale real-world problems, e.g. automation warehouse. The learning-based fully decentralized framework has been introduced to simultaneously alleviate real-time problem and pursuit the optimal planning policy. However, existing methods might generate significantly more vertex conflicts (called collision), which lead to low success rate or more makespan. In this paper, we propose a PrIoritized COmmunication learning method (PICO), which incorporates the implicit planning priorities into the communication topology within the decentralized multi-agent reinforcement learning framework. Assembling with the classic coupled planners, the implicit priority learning module can be utilized to form the dynamic communication topology, which also build an effective collision-avoiding mechanism. PICO performs significantly better in large-scale multi-agent path finding tasks in both success rates and collision rates than state-of-the-art learning-based planners.
View on arXiv