论文标题
多代理路径通过树LSTM查找
Multi-Agent Path Finding via Tree LSTM
论文作者
论文摘要
近年来，多试路径发现（MAPF）引起了两项操作研究（OR）和增强学习（RL）领域的关注。但是，在2021 Flatland3挑战赛中，在MAPF上的比赛中，最佳RL方法仅得分27.9，远低于最佳或方法。本文提出了针对Flatland3挑战的新RL解决方案，该解决方案得分为125.3，比以前最佳RL解决方案高几倍。我们创造性地将新颖的网络架构TreelstM应用于我们的解决方案中的MAPF。连同其他几种RL技术，包括奖励成型，多相训练和集中控制，我们的解决方案可与前2-3或方法相媲美。
In recent years, Multi-Agent Path Finding (MAPF) has attracted attention from the fields of both Operations Research (OR) and Reinforcement Learning (RL). However, in the 2021 Flatland3 Challenge, a competition on MAPF, the best RL method scored only 27.9, far less than the best OR method. This paper proposes a new RL solution to Flatland3 Challenge, which scores 125.3, several times higher than the best RL solution before. We creatively apply a novel network architecture, TreeLSTM, to MAPF in our solution. Together with several other RL techniques, including reward shaping, multiple-phase training, and centralized control, our solution is comparable to the top 2-3 OR methods.
