Outdated Talks and Publications

Invited Talks

• Games, Optimization, and Online Algorithms At INFORMS 2006 session on Online Convex Optimization, INFORMS, Pittsburgh, PA, November 8, 2006.
  
  
• 2006 AAAI Computer Poker Competition. At Twenty-First National Conference on Artificial Intelligence, Boston, MA, July 2006. Also see the news item published in JCGA.
  
  
• A survey of online convex programming. At AMS-AWM-MAA Special Session on Mathematical Results and Challenges in Learning Theory, Joint Mathematics Meetings, San Antonio, TX, January 12-15, 2006.
  
  
• Response regret. At Coevolutionary and Coadaptive Systems, AAAI Fall Symposia Series, Washington, DC, November 4-6, 2005.(slides)
  
  

Journal Publications

• A. Blum, T. Sandholm, and M. Zinkevich. Online algorithms for market clearing. In Journal of the ACM, to appear. A previous version appeared in Symposium on Discrete Algorithms, 2002.
  
  
• A. Blum, J. Jackson, T. Sandholm, and M. Zinkevich. Preference elicitation and query learning. Journal of Machine Learning Research 2004. A previous version appeared in Sixteenth Annual Conference on Computational Learning Theory, 2003.
  
  
• M. Zinkevich, A. Greenwald, M. Littman. A Hierarchy of Prescriptive Goals for Multiagent Learning. In Artificial Intelligence, to appear.
  
  

Refereed Publications

• M. Zinkevich, M. Bowling, M. Johanson, C. Piccione.Regret Minimization in Games with Incomplete Information. NIPS 2007.
  
  
• M. Johanson, M. Zinkevich, and M. Bowling. Computing robust counter-strategies. NIPS 2007.
  
  
• M. Zinkevich, M. Bowling, N. Burch.A New Algorithm for Generating Equilibria in Massive Zero-Sum Games. AAAI 2007.
  
  
• N. Ratliff, D. Bagnell, M. Zinkevich. Subgradient Methods for Structured Prediction. Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS-07), 2007.
  
  
• M. Littman, N. Ravi, A. Talwar, M. Zinkevich. An Efficient Optimal-Equilibrium Algorithm for Two-Player Game Trees. Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI-06), 2006.
  
  
• M. Zinkevich, M. Bowling, N. Bard, M. Kan, and D. Billings. Optimal Unbiased Estimators for Evaluating Agent Performance. Twenty-First National Conference on Artificial Intelligence (AAAI-06), 2006.
  
  
• A. Rettinger, M. Zinkevich, and M. Bowling. Boosting Expert Ensembles for Rapid Concept Recall. Twenty-First National Conference on Artificial Intelligence (AAAI-06), 2006.
  
  
• N. Sturtevant, M. Zinkevich, and M. Bowling. ProbMaxn: Opponent Modeling in N-Player Games. Twenty-First National Conference on Artificial Intelligence (AAAI-06), 2006.
  
  
• N. Ratliff, J. Bagnell, M. Zinkevich. Maximum Margin Planning. Twenty-Third International Conference on Machine Learning, 2006. A previous version appeared in Neural Information Processing Systems, Workshop on Machine Learning Based Robotics in Unstructured Environments.
  
  
• M. Zinkevich, A. Greenwald, and M. Littman. Cyclic equilibria in markov games. In Neural Information Processing Systems, 2005.
  
  
• M. Zinkevich. Theoretical guarantees for algorithms in multiagent settings. PhD thesis, Carnegie Mellon University, 2004
  
  
• M. Zinkevich, A. Blum, and T. Sandholm. On polynomial­time preference elicitation with value queries. In ACM Conference on Electronic Commerce, 2003.
  
  
• M. Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In Twentieth International Conference on Machine Learning, 2003.
  
  
J. Langford, M. Zinkevich, and S. Kakade. Competitive analysis of the explore/exploit tradeoff. In Nineteenth International Conference on Machine Learning, 2002.


• T. Balch and M. Zinkevich. Symmetry in markov decision processes and its implications for single agent and multiagent learning. In Eighteenth International Conference on Machine Learning, 2001.
  
  

Workshops

• T. Balch and M. Zinkevich. Using symmetry in asymmetrical markov decision processes (extended abstract). In Fifth International Conference on Autonomous Agents, Workshop on Learning Agents, 2001.