# Learning to Resolve Conflicts for Multi-Agent Path Finding with Conflict-Based Search

arXiv: https://arxiv.org/abs/2012.06005 · HTML: https://mlsanity.com/paper/2012.06005/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning](https://mlsanity.com/paper/2302.01578/) (2023)
- [Graph-Based Multi-Robot Path Finding and Planning](https://mlsanity.com/paper/2206.11319/) (2022)
- [Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding](https://mlsanity.com/paper/2308.05893/) (2023)
- [Leveraging Experience in Lifelong Multi-Agent Pathfinding](https://mlsanity.com/paper/2202.04382/) (2022)
- [The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications](https://mlsanity.com/paper/2203.07092/) (2022)
- [Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality](https://mlsanity.com/paper/2301.08451/) (2023)
- [Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation](https://mlsanity.com/paper/2603.23838/) (2026)

## Abstract (arXiv)

Conflict-Based Search (CBS) is a state-of-the-art algorithm for multi-agent path finding. At the high level, CBS repeatedly detects conflicts and resolves one of them by splitting the current problem into two subproblems. Previous work chooses the conflict to resolve by categorizing the conflict into three classes and always picking a conflict from the highest-priority class. In this work, we propose an oracle for conflict selection that results in smaller search tree sizes than the one used in previous work. However, the computation of the oracle is slow. Thus, we propose a machine-learning framework for conflict selection that observes the decisions made by the oracle and learns a conflict-selection strategy represented by a linear ranking function that imitates the oracle's decisions accurately and quickly. Experiments on benchmark maps indicate that our method significantly improves the success rates, the search tree sizes and runtimes over the current state-of-the-art CBS solver.