.png){kind=icon}
返回
Multi-agent policy transfer via task relationship modeling
.png){kind=icon}
PRE
AI
DOI：10.1007/s11432-023-3862-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous studies on multi-agent transfer learning have accommodated teams of different sizes but heavily relied on the generalization ability of neural networks for adapting to unseen tasks. We posit that the relationship among tasks provides key information for policy adaptation. We utilize this relationship for efficient transfer by attempting to discover and exploit the knowledge among tasks from different teams, proposing to learn an effect-based task representation as a common latent space among tasks, and using it to build an alternatively fixed training scheme. Herein, we demonstrate that task representation can capture the relationship among teams and generalize to unseen tasks. Thus, the proposed method helps transfer the learned cooperation knowledge to new tasks after training on a few source tasks. Furthermore, the learned transferred policies help solve tasks that are difficult to learn from scratch.
Keyword:
multi-agent reinforcement learning
cooperative transfer learning
task relationship modeling
multi-agent policy reuse
multi-agent multi-task learning
期刊
IF:
7.6
论文数:
4.9K
被引数:
8.9K
机构
引用论文
分享收藏分享收藏Isotope dilution analysis of polychlorinated biphenyls (PCBs) in transformer oil and global commercial PCB formulations by high resolution gas chromatography–high resolution mass spectrometry.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Relationship between osteonecrosis and antiphospholipid antibodies in patients with systemic lupus erythematosus: a systematic review protocol系统性红斑狼疮患者骨坏死与抗磷脂抗体的关系: 系统评价方案BMJ Open
OAAI
BMJ OpenIF0
OAAI分享收藏Reinforcement learning to adjust parametrized motor primitives to new situationsAUTONOMOUS ROBOTS
AUTONOMOUS ROBOTSIF4.3
PREAI
分享收藏
查看更多内容