Papers

• Online Databases: DBLP, CiteSeer, CSB.

Published / Under Review

• Auction-Based Multi-Robot Routing
  Michail G. Lagoudakis, Vangelis Markakis, David Kempee, Pinar Keskinocak, Sven Koenig, Craig Tovey, Anton Kleywegt, Adam Meyerson, and Sonal Jain.
  to appear in the Proceedings of Robotics: Science and Systems,
  MIT, Boston, MA, June 2005.

• Generation of Bidding Rules for Auction-Based Robot Coordination
  Craig Tovey, Michail G. Lagoudakis, Sonal Jain, and Sven Koenig.
  Proceedings of the 3rd International Multi-Robot Systems Workshop,
  Naval Research Laboratory, Washington, DC, March 2005.

• Simple Auctions with Performance Guarantees for Multi-Robot Task Allocation
  Michail G. Lagoudakis, Mark Berhault, Sven Koenig, Pinar Keskinocak, and Anton Kleywegt.
  Proceedings of the 2004 IEEE/JRS International Conference on Intelligent Robots and Systems (IROS 2004),
  Sendai, Japan, September 2004.

• Predicting Need for Urgent Endoscopy in Patients with Acute Gastrointestinal Bleeding
  Atul Kumar, Michail G. Lagoudakis, Bruce Kalmin, Bawna Halwan.
  ASGE Ninth Annual Young Investigators Conference in Digestive Diseases,
  Huntington Beach, CA, April 2004.

• Least-Squares Policy Iteration
  Michail G. Lagoudakis and Ronald Parr.
  Journal of Machine Learning Research, 4, 2003, pp. 1107-1149.

• Reinforcement Learning as Classification: Leveraging Modern Classifiers
  Michail G. Lagoudakis and Ronald Parr.
  Proceedings of the 20th International Conference on Machine Learning (ICML-2003),
  Washington, D.C., August 2003, pp. 424-431.

• Approximate Policy Iteration using Large-Margin Classifiers
  Michail G. Lagoudakis and Ronald Parr.
  Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI-03),
  Acapulco, Mexico, August 2003, pp. 1432-1434.

• Learning in Zero-Sum Team Markov Games using Factored Value Functions
  Michail G. Lagoudakis and Ronald Parr.
  Proceedings of NIPS*2002: Neural Information Processing Systems: Natural and Synthetic,
  Vancouver, BC, December 2002, pp. 1659-1666.

• A Listening Keyboard for Users with Motor Impairments -- A Usability Study
  Bill Manaris, Valanne MacGyvers and Michail G. Lagoudakis.
  International Journal of Speech Technology, 5, 2002, pp. 371-388.

• Value Function Approximation in Zero-Sum Markov Games
  Michail G. Lagoudakis and Ronald Parr.
  Proceedings of the 18th Conference on Uncertainty in Artificial Intelligence (UAI 2002),
  Edmonton, Alberta, Canada, August 1-4, 2002, pp. 283-292.

• Coordinated Reinforcement Learning
  Carlos Guestrin, Michail G. Lagoudakis and Ronald Parr.
  Proceedings of the 19th International Conference on Machine Learning (ICML-2002),
  University of New South Wales, Sydney, Australia, July 2002, pp. 227-234.

• Least-Squares Methods in Reinforcement Learning for Control
  Michail G. Lagoudakis, Ronald Parr and Michael L. Littman.
  Lecture Notes on Artificial Intelligence, Vol. 2308, Springer, 2002, pp. 249-260.
  Proceedings of the 2nd Hellenic Conference on Artificial Intelligence (SETN-02),
  Thessaloniki, Greece, April 11-12, 2002.

• Model-Free Least-Squares Policy Iteration
  Michail G. Lagoudakis and Ronald Parr.
  Proceedings of NIPS*2001: Neural Information Processing Systems: Natural and Synthetic,
  Vancouver, BC, December 2001, pp. 1547-1554.

• Selecting the Right Algorithm
  Michail G. Lagoudakis, Michael L. Littman and Ronald Parr.
  Proceedings of the 2001 AAAI Fall Symposium Series: Using Uncertainty within Computation,
  Cape Cod, MA, November 2001.

• Learning to Select Branching Rules in the DPLL Procedure for Satisfiability
  Michail G. Lagoudakis and Michael L. Littman.
  Electronic Notes in Discrete Mathematics (ENDM), Vol. 9,
  LICS 2001 Workshop on Theory and Applications of Satisfiability Testing (SAT 2001),
  Boston, MA, June 14-15, 2001. (ENDM Volume 9 online)

• Algorithm Selection using Reinforcement Learning
  Michail G. Lagoudakis and Michael L. Littman.
  Proceedings of the 17th International Conference on Machine Learning,
  Stanford, CA, June 2000, pp. 511-518.

• Reinforcement Learning for Algorithm Selection
  Michail G. Lagoudakis and Michael L. Littman. Student Abstract.
  Proceedings of the 17th National Conference on Artificial Intelligence AAAI-00,
  Austin, TX, July 2000, pp. 1081.

• 2D DNA Self-Assembly for Satisfiability
  Michail G. Lagoudakis and Thomas H. LaBean.
  Proceedings of the 5th DIMACS International Meeting on DNA Based Computers,
  MIT, Boston, MA, June 1999, pp. 139-152.

• Neural Maps for Mobile Robot Navigation
  Michail G. Lagoudakis and Anthony S. Maida.
  Proceedings of the 1999 IEEE International Joint Conference on Neural Networks,
  Washington, D.C., July 1999.

• Robot Navigation with a Polar Neural Map
  Michail G. Lagoudakis and Anthony S. Maida. Student Abstract,
  Proceedings of the 16th National Conference on Artificial Intelligence AAAI-99,
  Orlando, FL, July 1999, pp. 965.

• A Polar Neural Map for Mobile Robot Local Navigation
  Michail G. Lagoudakis and Anthony S. Maida. Extended Abstract,
  Proceedings of the International Conference on Cognitive and Neural Systems 1999,
  Boston University, Boston, MA, May 1999.

• An IDA* Algorithm for Optimal Spare Allocation
  Michail G. Lagoudakis
  Proceedings of 1999 ACM Symposium on Applied Computing,
  San Antonio, TX, February 1999, pp. 486-488.

• Universal Access to Mobile Computing Devices through Speech Input
  Bill Z. Manaris, Vallane MacGyvers, and Michail G. Lagoudakis
  Proceedings of the 12th International Florida Artificial Intelligence Research Symposium (FLAIRS-99),
  Orlando, FL, May 1999, pp. 286-292.

• Book Review: Artificial Intelligence and Scientific Method
  Journal of Intelligent and Robotic Systems, 22, 1998, pp. 87-95.

  
   

Unpublished

• Using Markov Decision Processes and Reinforcement Learning to solve the ``Local vs. Remote'' Execution Problem
  With Tammy L. Bailey and Nicoleta Popoviciu, 2000.

• Balancing and Control of a Freely-Swinging Pendulum using a Model-Free Reinforcement Learning Algorithm, 1999.

• N-SAT: A Numerical Approach to Satisfibility, 1999.

• Nonlinear Dynamics of Video Feedback
  With Timothy H. Burt, 1999.

• Linear Planning in the Cognitive Map, 1998.

• Experimental Comparison of the Speech Understanding and the Hand-Stick Methods
  as Computer Input Modalities for Motor-Challenged Users
  Technical Report, USL-HCIL-1998-01, Human-Computer Interaction Lab,
  Computer Science Department, University of Louisiana, Lafayette, 1998.

• Mobile Robot Local Navigation with a Polar Neural Map
  M.Sc. Thesis, Center for Advanced Computer Studies, University of Louisiana, Lafayette, 1998.

• Spatial Knowledge in Humans, Animals and Robots, 1998.

• Near Optimal Solutions for the Minimum Cost Spare Allocation Problem
  using Hopfield-Type Neural Network Optimizers,
  with Anthony S. Maida, 1998.

• A Hopfield Neural Network for Dynamic Path Planning and Obstacle Avoidance, 1997.

• Planning and Intelligent Systems: An Introductory Overview
  Technical Report, CACS TR-96-2-1, CACS, University of Louisiana, Lafayette, 1996.

• The 0-1 Knapsack Problem, 1996.

• Implementation of a Knowledge-Based Scheduler for Job-Shop Production Environments
  Diploma Thesis (in Greek), Computer Engineering and Informatics Department,
  University of Patras, Greece, 1995.

Home