.png){kind=icon}
Return
Mean-Field Deep Reinforcement Learning for Multi-Agent Path Finding
.png){kind=icon}
PRE
AI
DOI：10.1109/LRA.2026.3669783.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Continuous-space multi-agent path finding (MAPF) presents severe challenges for deep reinforcement learning (DRL), as joint state–action spaces grow exponentially and fine-grained inter-agent coordination is required. Applying mean-field approximation can reduce input complexity from $\mathcal {O}(N^{2}~d)$ to $\mathcal {O}(Nd)$, but naively averaging neighbors may weaken critical local interactions, limiting planning success. To address this, we propose the Mean-Field Multi-Agent Reinforcement Pathfinding Framework (MAMFRPF), which integrates mean-field interaction compression, a dual-stream local mean-field critic, trust-region policy optimization, and a sparse-reward design. The dual-stream critic compensates for information loss caused by mean-field averaging, improving planning success by over 20 percentage points under partial observability, while training time is reduced by roughly 7%. Trust-region optimization ensures monotonic policy improvement, and the sparse-reward mechanism accelerates long-horizon credit assignment. Experiments on continuous MAPF benchmarks show that MAMFRPF outperforms strong baselines by 15% in success rate, scales with agent density, and generalizes across diverse spatial layouts.
Keywords:
Mean-field reinforcement learning
multi-agent path finding
deep reinforcement learning
coordination and scalability
continuous control
Journal
I
IF:
5.3
Papers:
1.9K
Citations:
3.9W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
View more