Publication - Combining Dynamic Reward Shaping and Action Shaping for Coordinating Multi-Agent Learning
| Authors: | Zhu, Xiangbin; Zhang, Chongjie; Lesser, Victor | ||||
| Title: | Combining Dynamic Reward Shaping and Action Shaping for Coordinating Multi-Agent Learning | ||||
| Abstract: | Coordinating multi-agent reinforcement learning provides a promising approach to scaling learning in large cooperative multi-agent systems. It allows agents to learn local decision policies based on their local observations and rewards, and, meanwhile, coordinates agents´ learning processes to ensure the global learning performance. One key question is that how coordination mechanisms impact learning algorithms so that agents´ learning processes are guided and coordinated. This paper presents a new shaping approach that effectively integrates coordination mechanisms into local learning processes. This shaping approach uses two-level agent organization structures and combines reward shaping and action shaping. The higher-level agents dynamically and periodically produce the shaping heuristic knowledge based on the learning status of the lower-level agents. The lower-level agents then uses this knowledge to coordinate their local learning processes with other agents. Experimental results show our approach effectively speeds up the convergence of multi-agent learning in large systems. | ||||
| Keywords: | Learning, Multi-Agent Systems, Organizational Control | ||||
| Publication: | Proc. of 2013 IEEE/WIC/ACM International Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), Vol: 2, pp. 321 - 328 | ||||
| Location: | Atlanta, GA | ||||
| Publisher: | IEEE Computer Society Press | ||||
| Date: | 2013 | ||||
| Sources: |
PDF: /Documents/lesser/zhu_IAT13.pdf HTML: http://doi.ieeecomputersociety.org/10.1109/WI-IAT.2013.127 |
||||
| Reference: | Xiangbin Zhu, Chongjie Zhang, Victor Lesser (2013). "Combining Dynamic Reward Shaping and Action Shaping for Coordinating Multi-agent Learning," Proc. of IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), Vol. 2, pp. 321-328. [View Details]
|
||||
| bibtex: | @inproceedings{Zhu-523,
author = "Xiangbin Zhu and Chongjie Zhang and Victor Lesser",
title = "{Combining Dynamic Reward Shaping and Action
Shaping for Coordinating Multi-Agent Learning}",
booktitle = "Proc. of 2013 IEEE/WIC/ACM International
Conferences on Web Intelligence (WI) and
Intelligent Agent Technologies (IAT)",
volume = "2",
publisher = "IEEE Computer Society Press",
pages = "321-328",
year = "2013",
address = "Atlanta, GA",
url = "http://mas.cs.umass.edu/paper/523",
}
|
||||
