# Multi-Agent Path Finding via Tree LSTM

arXiv: https://arxiv.org/abs/2210.12933 · HTML: https://mlsanity.com/paper/2210.12933/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Flatland-RL : Multi-Agent Reinforcement Learning on Trains](https://mlsanity.com/paper/2012.05893/) (2020)
- [Multi-Agent Path Finding with Delay Probabilities](https://mlsanity.com/paper/1612.05309/) (2016)
- [Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World](https://mlsanity.com/paper/2103.16511/) (2021)
- [Multi-Agent Path Finding with Deadlines](https://mlsanity.com/paper/1806.04216/) (2018)
- [On the Computational Complexity of Multi-Agent Pathfinding on Directed Graphs](https://mlsanity.com/paper/1911.04871/) (2019)

## Built on by (most cited first, 1 of 1)

- [Towards Autonomous Railway Operations: A Semi-Hierarchical Deep Reinforcement Learning Approach to the Vehicle Rescheduling Problem](https://mlsanity.com/paper/2605.10257/) (2026)

## Abstract (arXiv)

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.