Presentations

 Invited Talks and Conference Presentations

• Efficient Approximate Policy Iteration Methods for Sequential Decision Making in Reinforcement Learning
  Talk given at the School of Computer Science, Carnegie Mellon University,
  Pittsburgh, PA, October 14, 2003.

• Reinforcement Learning as Classification: Leveraging Modern Classifiers
  Talk given at the Workshop on Machine Learning Reductions,
  Toyota Technological Institute, Chicago, IL, September 11, 2003.

• Reinforcement Learning as Classification: Leveraging Modern Classifiers
  Talk given at the 20th International Conference on Machine Learning,
  Washington, DC, August 22, 2003.

• Approximate Policy Iteration using Modern Classifiers
  Poster presented at the 18th International Joint Conference on Artificial intelligence,
  Acapulco, Mexico, August 13, 2003.

• Efficient Approximate Methods for Sequential Decision Making in Reinforcement Learning
  Talk given at the Institute of Computer Science, Foundation of Research and Technology - Hellas (FORTH),
  Herakleion, Crete, Hellas (Greece), July 23, 2003.
  Same talk also given at the Department of Electronic and Computer Engineering, Technical University of Crete,
  Hania, Crete, Hellas (Greece), July 18, 2003.

• Linear Architectures and Least-Squares Methods in Reinforcement Learning for Control
  Talk given at the National Center for Scientific Research "Demokritos",
  Athens, Hellas (Greece), December 20, 2002.

• Learning in Zero-Sum Team Markov Games using Factored Value Functions
  Poster presented at NIPS*2002: Neural Information Processing Systems: Natural and Synthetic,
  Vancouver, BC, December 2002.
  

• Value Function Approximation in Zero-Sum Markov Games
  Poster presented at UAI-2002: Uncertainty in Artificial Intelligence,
  Edmonton, Alberta, Canada, August 2002.
  

• Coordinated Reinforcement Learning
  Poster presented at the 19th International Conference on Machine Learning,
  Sydney, Australia, July 2002.
  

• Least-Squares Methods in Reinforcement Learning for Control (in Greek)
  Talk given at the 2nd Hellenic Conference on Artificial Intelligence (SETN-02),
  Thessaloniki, Greece, April 11-12, 2002.

• Model-Free Least-Squares Policy Iteration
  Poster presented at NIPS*2001: Neural Information Processing Systems: Natural and Synthetic,
  Vancouver, BC, December 2001.
  

• Selecting the Right Algorithm
  Talk given at 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
  Talk given at the LICS 2001 Workshop on Theory and Applications of Satisfiability Testing (SAT 2001),
  Boston, MA, June 14-15, 2001.

• Algorithm Selection using Reinforcement Learning
  Talk given at the 17th International Conference on Machine Learning,
  Stanford, CA, June 2000.

• Reinforcement Learning for Algorithm Selection
  Poster presented at the 17th National Conference on Artificial Intelligence AAAI-00,
  Austin, TX, July 2000.

• 2D DNA Self-Assembly for Satisfiability
  Talk given at the 5th DIMACS International Meeting on DNA Based Computers,
  MIT, Boston, MA, June 1999.

• Neural Maps for Mobile Robot Navigation
  Talk given at the 1999 International Joint Conference on Neural Networks,
  Washington, D.C., July 1999.

• Robot Navigation with a Polar Neural Map
  Poster presented at the 16th National Conference on Artificial Intelligence AAAI-99,
  Orlando, FL, July 1999.

• A Polar Neural Map for Mobile Robot Local Navigation
  Poster presented at the International Conference on Cognitive and Neural Systems 1999,
  Boston University, Boston, MA, May 1999.

• An IDA* Algorithm for Optimal Spare Allocation
  Talk given at the 1999 ACM Symposium on Applied Computing,
  San Antonio, TX, February 1999.

• Mobile Robot Navigation with Neural Maps
  Talk given at CPS 300 - Graduate Student Seminar,
  Department of Computer Science, Duke University, November 1998.

 Research Seminars, Class Lectures, and Other Presentations

• Efficient Approximate Policy Iteration Methods for Sequential Decision Making in Reinforcement Learning
  (also available in 8 up format)
  Ph.D. Defense Talk,
  Department of Computer Science, Duke University, April 18, 2003.

• Least-Squares Methods in Reinforcement Learning for Control
  (also available in 8 up format)
  Ph.D. Preliminary examination talk,
  Department of Computer Science, Duke University, May 13, 2002.

• LSPI: Least-Squares Policy Iteration
  Talk given at the Artificial Intelligence Seminar,
  Department of Computer Science, Duke University, May 2002.
  

• Model-Free Least-Squares Policy Iteration
  Talk given at the Scientific Computing Seminar,
  Department of Computer Science, Duke University, November 30, 2001.
  

• "Do the Right Thing": Algorithm Selection using Reinforcement Learning
  Talk at the First Annual Graduate Student Research Day,
  Office of Graduate Student Affairs, Duke University, April 2001.
  

• Learning to Select Branching Rules in the DPLL Procedure for Satisfiability
  Talk given at the Algorithms Seminar,
  Department of Computer Science, Duke University, April 6, 2001.
  

• Satisfiability
  Class Lecture for CPS 271 "Numeric Artificial intelligence",
  Department of Computer Science, Duke University, Spring 2001.
  

• Reinforcement Learning
  Class Lecture for CPS 370 "Planning Under Uncertainty",
  Department of Computer Science, Duke University, Fall 2000.
  

• Run-time Algorithm Selection using Reinforcement Learning
  2nd Year Research Project Presentation Talk,
  Department of Computer Science, Duke University, April 26, 2000.
  

• Using Markov Decision Processes and Reinforcement Learning to solve the ``Local vs. Remote'' Execution Problem
  Project Presentation Talk for CPS 210 "Operating Systems",
  Department of Computer Science, Duke University, April 2000.
  

• Divide Or Conquer?
  Talk given at the Algorithms Seminar,
  Department of Computer Science, Duke University, December 10, 1999.
  

• Mobile Robot Local Navigation with a Polar Neural Map
  Poster of my Master's thesis,
  Center for Advanced Computer Studies, University of Louisiana, Lafayette, May 1998.

Home