.png){kind=icon}
.png){kind=icon}
Return
Algorithmically-designed reward shaping for multiagent reinforcement learning in navigation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.131654.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A new approach that uses well-known single-agent pathfinding algorithms for semi-automated MARL reward shaping, reducing manual effort. • Tested in diverse multiagent navigation environments, proving versatility and robustness. • Trains up to 2× faster than state-of-the-art, reducing training time and computational costs. • Achieves up to 20% higher rewards than state-of-the-art, demonstrating its ability to deliver more optimised solutions. • Makes MARL more accessible to non-domain experts and scalable for complex multiagent systems.
Keywords:
Multiagent reinforcement learning (MARL)
Reward shaping
Navigation
Packet routing
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.