Scaling up multi-agent reinforcement learning in complex domains
TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neigh...
Saved in:
| Main Authors: | , |
|---|---|
| 格式: | text |
| 語言: | English |
| 出版: |
Institutional Knowledge at Singapore Management University
2008
|
| 主題: | |
| 在線閱讀: | https://ink.library.smu.edu.sg/sis_research/6798 https://ink.library.smu.edu.sg/context/sis_research/article/7801/viewcontent/Scaling_Up_IAT08.pdf |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (TD) methods for real-time reinforcement learning. In this paper, we present two strategies, i.e. policy sharing and neighboring-agent mechanism, to further improve the learning efficiency of TD-FALCON in complex multi-agent domains. Through experiments on a traffic control problem domain and the herding task, we demonstrate that those strategies enable TD-FALCON to remain functional and adaptable in complex multi-agent domains |
|---|