Research

Systems and Papers

Consumer Website: iLifeCoach

Program developed:A Java program for calculating Nash equilibrium for 2-person normal-form games. See a Java applet showing the program (source code available). By using Lemke-Howson algorithm, we are able to derive Nash equilibrium for any-size 2-person game. Our program is faster than Gambit

Papers:

Junling Hu, Fabrizio Morbini, Fuliang Weng and Xue Liu, Dynamic N-best Selection and Its Application in Dialog Act Detection, Proceedings of the 8^th SIGDial workshop on Discourse and Dialogue, 59-62, September 2007

Fuliang Weng, Ye-Yi Wang, Gokhan Tur and Junling Hu. (Editors) Proceedings of the Workshop on Bridging the Gap of Academic and Industrial Research in Dialog Technologies, the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), Rochester, NY, April 2007.

Junling Hu, Fabrizio Morbini, Feng Lin and Fuliang Weng. Learning-based Semantic Interpreter in a Dialog System, March 2007

Junling Hu and Michael P. Wellman, Nash Q-Learning for General-Sum Stochastic Games [pdf] , Journal of Machine Learning Research, 4(Nov):1039-1069, 2003

Junling Hu, Dynamic Pricing Agents and Multiagent Learning [pdf], 2002

Junling Hu and Yilian Zhang, Online Reinformcenet Learning in Multiagent Systems [pdf] [ps], 2002

Junling Hu and Michael P. Wellman, Online Learning about Other Agents in a Dynamic Multiagent System [pdf], Journal of Cognitive System Research 2(1), 2001, page 67-79, Elsevier Science

Junling Hu and Michael P. Wellman, Experimental Results of Multiagent Reinforcement Learning [pdf], Proceedings of the Seventeenth International Conference on Machine Learning (ICML-2000) , AAAI Press, San Francisco, July 2000

Junling Hu, Daniel Reeves and Hock-Shan Wong, Personalized Bidding agents for Online Auctions [pdf], Proceedings of The Fifth International Conference on The Practical Application of Intelligent Agents and Multi-Agents, Manchester, UK, May 2000

Junling Hu Learning in Dynamic Noncooperative Muiltiagent Systems [pdf], Ph.D. thesis, June 1999

Junling Hu, Daniel Reeves and Hock-Shan Wong, Agent Service for Online Auctions [html], Proceedings of the AAAI-99 workshop on AI for Electronic Commerce, AAAI Press, 1999

Junling Hu, Learning in Markov Games with Incomplete Information [ps] (abstract), Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), AAAI Press, 1998

Junling Hu and Michael P. Wellman, Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm [pdf] [ps], Proceedings of the Fifteenth International Conference on Machine Learning (ICML-98)

Junling Hu and Michael P. Wellman, Online learning about other agents in dynamic multiagent systems , Proceedings of the Second International Conference on Autonomous Agents (Agents '98)

Michael P. Wellman and Junling Hu, Conjectural equilibrium in multiagent learning [pdf] , Machine Learning 33, page 1-23,1998.

Junling Hu and Michael P. Wellman, Self-fulfilling Bias in Multiagent Learning, Proceedings of the Second International Conference on Multiagent Systems (ICMAS-96), AAAI Press, 1996