Publication - Learning Quantitative Knowledge for Multiagent Coordination

Authors:	Jensen, David; Atighetchi, Michael; Vincent, Régis; and Lesser, Victor
Title:	Learning Quantitative Knowledge for Multiagent Coordination
Abstract:	A central challenge of multiagent coordination is reasoning about how the actions of one agent affect the actions of another. Knowledge of these interrelationships can help coordinate agents -- preventing conflicts and exploiting beneficial relationships among actions. We explore three interlocking methods that learn quantitative knowledge of such non-local effects in TÆMS, a well-developed framework for multiagent coordination. The surprising simplicity and effectiveness of these methods demonstrates how agents can learn domain-specific knowledge quickly, extending the utility of coordination frameworks that explicitly represent coordination knowledge.
Keywords:	Diagnosis, JAF, Learning, Survivability, TAEMS
Publication:	16th National Conference on Artificial Intelligence (AAAI-99), pp. 24 - 31
Location:	Orlando, FL.
Publisher:	American Association for Artificial Intelligence
Date:	August 1999
Sources:	PS: http://mas.cs.umass.edu/~vincent/papers/AAAI-99/1999-04.ps.gz HTML: http://mas.cs.umass.edu/~vincent/papers/AAAI-99/index.html PDF: /Documents/1999-04.pdf
Reference:	Jensen, David; Atighetchi, Michael; Vincent, Régis; and Lesser, Victor. Learning Quantitative Knowledge for Multiagent Coordination. 16th National Conference on Artificial Intelligence (AAAI-99), American Association for Artificial Intelligence, pp. 24-31. August 1999.
`bibtex`:	@article{Jensen-124, author = "David Jensen and Michael Atighetchi and Régis Vincent and Victor Lesser", title = "{Learning Quantitative Knowledge for Multiagent Coordination}", journal = "16th National Conference on Artificial Intelligence (AAAI-99)", publisher = "American Association for Artificial Intelligence", pages = "24-31", month = "August", year = "1999", address = "Orlando, FL.", url = "http://mas.cs.umass.edu/paper/124", }