In this work we study a well-known and challenging problem of Multi-agent Pathfinding, when a set of agents is confined to a graph, each agent is assigned a unique start and goal vertices and the task is to find a set of collision-free paths (one for each agent) such that each agent reaches its respective goal. We investigate how to utilize Monte-Carlo Tree Search (MCTS) to solve the problem. Although MCTS was shown to demonstrate superior performance in a wide range of problems like playing antagonistic games (e.g. Go, Chess etc.), discovering faster matrix multiplication algorithms etc., its application to the problem at hand was not well studied before. To this end we introduce an original variant of MCTS, tailored to multi-agent pathfinding. The crux of our approach is how the reward, that guides MCTS, is computed. Specifically, we use individual paths to assist the agents with the the goal-reaching behavior, while leaving them freedom to get off the track if it is needed to avoid collisions. We also use a dedicated decomposition technique to reduce the branching factor of the tree search procedure. Empirically we show that the suggested method outperforms the baseline planning algorithm that invokes heuristic search, e.g. A*, at each re-planning step.

翻译：本文研究了一个众所周知且具有挑战性的多智能体路径规划问题：当一组智能体被限制在一个图中，每个智能体被分配唯一的起点和目标顶点时，任务是找到一组无碰撞路径（每个智能体一条），使得每个智能体到达其各自的目标。我们探讨如何利用蒙特卡洛树搜索（MCTS）来解决该问题。尽管MCTS已在广泛的问题中展现出卓越性能，例如对抗性游戏（如围棋、国际象棋等）、发现更快的矩阵乘法算法等，但其在此问题上的应用此前尚未得到充分研究。为此，我们提出了一种针对多智能体路径规划量身定制的MCTS原创变体。我们方法的核心在于指导MCTS的奖励如何计算。具体而言，我们利用个体路径来辅助智能体实现目标到达行为，同时在需要避免碰撞时给予它们偏离路径的自由。我们还使用了一种专门的分解技术来降低树搜索过程的分支因子。实验表明，我们所提出的方法优于在每个重规划步骤中调用启发式搜索（例如A*）的基线规划算法。