Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding

About

Multi-Agent Reinforcement Learning (MARL) based Multi-Agent Path Finding (MAPF) has recently gained attention due to its efficiency and scalability. Several MARL-MAPF methods choose to use communication to enrich the information one agent can perceive. However, existing works still struggle in structured environments with high obstacle density and a high number of agents. To further improve the performance of the communication-based MARL-MAPF solvers, we propose a new method, Ensembling Prioritized Hybrid Policies (EPH). We first propose a selective communication block to gather richer information for better agent coordination within multi-agent environments and train the model with a Q learning-based algorithm. We further introduce three advanced inference strategies aimed at bolstering performance during the execution phase. First, we hybridize the neural policy with single-agent expert guidance for navigating conflict-free zones. Secondly, we propose Q value-based methods for prioritized resolution of conflicts as well as deadlock situations. Finally, we introduce a robust ensemble method that can efficiently collect the best out of multiple possible solutions. We empirically evaluate EPH in complex multi-agent environments and demonstrate competitive performance against state-of-the-art neural methods for MAPF. We open-source our code at https://github.com/ai4co/eph-mapf.

Huijie Tang, Federico Berto, Jinkyoo Park• 2024

Related benchmarks

TaskDatasetResultRank
Multi-Agent Path Finding (MAPF)random 32x32-20
Success Rate100
77
Multi-Agent Path Finding (MAPF)random 64x64-20
Success Rate98
73
Multi-Agent Path Finding (MAPF)den312d 65x81
Success Rate100
32
Multi-Agent Path Finding (MAPF)warehouse 161x63
Success Rate100
31
Multi-Agent Path FindingRandom Map 120x120, 0.3 density
Success Rate93
15
Multi-Agent Path FindingRandom Map 240x240, 0.3 density
Success Rate (SR)94
15
Showing 6 of 6 rows

Other info

Follow for update