.png){kind=icon}
Return
Multi-agent proximal policy optimization supported dynamic behavior tree evolution for multi-agent systems
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2026.113841.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Hybrid method combining MAPPO and dynamic BT evolution for decision-making. • MAPPO-learned policies adapt BT structure to environmental changes in agents. • Agents autonomously update their BTs, enabling scalable decentralized systems. • Optimized BTs in MAPPO improve task propagation and reduce completion time. • MAPPO and BT modularity enhance decision-making in complex multi-agent systems.
Journal
IF:
8
Papers:
5.7K
Citations:
3.5W
Organization
Cited Papers
.png){kind=icon}
ShareSaveReconciling deep learning with symbolic artificial intelligence: representing objects and relations
OAAI
OAAIShareSaveShareSaveShareSave
View more