Manuela M. Veloso. Academic Positions. Education. Honors and Awards

Transcription

1 Manuela M. Veloso Computer Science Department, Carnegie Mellon University, Pittsburgh PA (412) , mmv/ Home address: 6645 Woodwell Street, Pittsburgh PA Citizenship: U.S.A. Born: Lisbon, Portugal, August 12, 1957 Married; Two sons, born 1981 and 1987 Academic Positions 07/02 - present Professor, Computer Science Department, Carnegie Mellon University 07/99-07/02 Tenured Associate Professor, Computer Science Department, Carnegie Mellon University 08/99-08/00 Visiting Associate Professor, Electrical Engineering and Computer Science Department, AI Lab, Massachusetts Institute of Technology, on sabbatical leave from Carnegie Mellon University 07/97-07/99 Associate Professor, Computer Science Department, Carnegie Mellon University 09/92-06/97 Assistant Professor Computer Science Department, Carnegie Mellon University 08/87-08/92 Research Assistant in Computer Science, Carnegie Mellon University 01/85-07/86 Teaching Assistant/Lecturer in Computer Science, Boston University 10/80-07/84 Teaching Assistant/Lecturer in Electrical and Computer Engineering, Instituto Superior Técnico, Lisbon, Portugal Education 1992 Ph.D. in Computer Science School of Computer Science, Carnegie Mellon University, Pittsburgh 1986 M.A. in Computer Science Computer Science Department, Boston University, Boston 1984 M.Sc. in Electrical and Computer Engineering Electrical and Computer Engineering Department, Instituto Superior Técnico, Lisbon, Portugal 1980 Licenciatura in Electrical Engineering Electrical and Computer Engineering Department, Instituto Superior Técnico, Lisbon, Portugal Honors and Awards 2003 AAAI Fellow (Fellow of the American Association of Artificial Intelligence) 2003 RoboCup-03: 4th place: Sony Legged-Robot and Small-Size Robot Leagues 2003 RoboCup American Open: 1st place: Sony Legged-Robot and Small-Size Robot Leagues 2002 RoboCup-02: 1st place Sony Legged-Robot League 2001 RoboCup-01: 2nd place Sony Legged-Robot League 2000 RoboCup-00: 3rd place: Simulator and Sony Legged-Robot Leagues 1999 RoboCup-99: 1st place Simulator League; 3rd place Sony Legged-Robot League 1998 RoboCup-98: 1st place: Simulator, Small-Size Robot, and Sony Legged-Robot Leagues 1997 Allen Newell Excellence in Research Award 1997 RoboCup-97: 1st place Small-Size Robot League; 3rd place Simulator League 1995 NSF Career Award Finmeccanica Chair 1986 AT&T Information Systems Award for Outstanding Academic Achievement Fellowship from the National Institute for Scientific Research, Portugal 1

2 Research Interests My long-term research goal is the effective construction of autonomous agents where cognition, perception, and action are combined to address planning, execution, and learning tasks. My vision is that multiple intelligent robots with different sets of complementary capabilities will provide a seamless synergy of intelligence. Concretely, my research focuses on the continuous integration of reactive, deliberative planning, and control learning for teams of multiple agents acting in adversarial, dynamic, and uncertain environments. Multiagent learning, adversarial modeling, advice generation, reuse, and space and temporal abstraction are of particular interest. My multiagent and multirobot research interests have been motivated by and experimented in the domain of robot soccer. I continue to investigate effective planning, execution, and learning algorithms for deterministic and nondeterministic multiagent domains within my research projects CORAL (Collaborate, Observe, Reason, Act, and Learn), MAPEL (Multi-Agent Planning, Execution, and Learning), and the RoboSoccer and MultiRobot Lab. I have also researched on control learning approaches to automating the modeling and optimization of the performance of signal processing transforms. Teaching Experience CMRoboBits: Creating an Intelligent AIBO Robot Fall 03 Artificial Intelligence (undergraduate) Fall 01, Fall 00, Fall 98, Spring 97, Spring 96, Fall 95. Artificial Intelligence (graduate) Spring 03, Spring 98, Spring 95, Spring 94, Spring 93. Planning, Execution, and Learning (graduate) Fall 02, Fall 01, Spring 99, Fall 97. Multiagent Systems: Theory and Hands-On Experience (graduate) Spring 01. Embodied Intelligence - MIT 6.836, Spring 00. Artificial Intelligence - MIT 6.034, Fall 99. Fundamentals of Computer Science (undergraduate) Fall 93. Several conference tutorials and short courses on Robotic Soccer (Agents-99, AAAI-99, IJCAI-99) and on Planning and Learning (ICML-95, IJCAI-95, FirstUSA, CMU Summer courses). Current Ph.D. Students Laurie Hiyakumoto (Fall 98, co-advised with Jaime Carbonell). Thesis proposal presented in November 2001 on Planning and Execution for Open-Domain Question Answering. Thesis committee: Manuela Veloso, co- Chair, Jaime Carbonell, co-chair, Jamie Callan, Eric Nyberg, Martha Pollack (University of Michigan). Scott Lenser (Fall 98). Thesis proposal presented in September 2002 on On-Line Robot Adaptation to Environment Change. Thesis committee: Manuela Veloso, Chair, Takeo Kanade, Sebastian Thrun, Minoru Asada (Osaka University). Elly Winner (Fall 98). Thesis proposal presented in October 2002 on Acquiring Domain-Specific Planners by Example. Thesis committee: Manuela Veloso, Chair, Avrim Blum, Reid Simmons, Leslie Kaebling (Massachusetts Institute of Technology). Patrick Riley (Fall 99). Thesis proposal presented in October 2002 on Any Team Coaching. Thesis committee: Manuela Veloso, Chair, Tom Mitchell, Jack Mostow, Milind Tambe (University of Southern California). James Bruce (Fall 00). Research: Vision, path planning, and learning in multirobot systems. Maayan Roth (Fall 01, co-advised with Reid Simmons). Research: Multirobot coordination. Douglas Vail (Fall 01). Research: Planning and learning in multiagent systems. Past Ph.D. Students Rune Jensen, co-advised with Randy Bryant, Ph.D. June Efficient BDD-based Search for Planning. Assistant Professor, ITU (Information Technology University), Copenhagen, Denmark. Michael Bowling, Ph.D. May Multiagent Learning in the Presence of Agents with Realistic Limitations. Assistant Professor, University of Alberta, Edmonton, Canada. Paul Carpenter, M.Sc. May Research Assistant, Institute for Creative Technologies (ICT), USC, Marina del Rey, CA. 2

3 William Uther, Ph.D. August Tree Based Hierarchical Reinforcement Learning. Research Assistant Professor, University of New South Wales, Sydney, Australia. Belinda Thom, Ph.D. December Interactive, Customized Generation of Jazz Improvisation: Believable Music Companions. Assistant Professor, Harvey Mudd College, CA. Bryan Singer, Ph.D. December Automating the Modeling and Optimization of the Performance of Signal Processing Algorithms. NSA (The National Security Agency), DC. Peter Stone, Ph.D. December Layered Learning in Multi-Agent Systems. Assistant Professor at University of Texas, Austin. Astro Teller, Ph.D. December Algorithm Evolution with Internal Reinforcement for Signal Understanding. CEO and co-founder of BodyMedia, Inc., Pittsburgh, PA. Kwun Han. Left the PhD program to join a start-up company in December Karen Zita Haigh. Ph.D. May Situation-Dependent Learning for Interleaved Planning and Robot Execution. Honeywell, Minneapolis, MN. Yury Smirnov. Ph.D. August Hybrid Algorithms for On-Line and Combinatorial Optimization Problems. CEO of Akonite, Inc, Palo Alto, CA. Professional Activities and Press Editorial Board: Journal of Artificial Intelligence Research, International Journal of Autonomous Agents and Multi- Agent Systems Reviewer: Artificial Intelligence, Journal of Artificial Intelligence Research, Machine Learning, Autonomous Robots Member of: AAAS, AAAI, AAAI Executive Council Member, IEEE Vice President and Trustee: RoboCup Federation General Chair: First RoboCup American Open 2003, Carnegie Mellon, Pittsburgh, April 30 May 4, 2003 General Chair: RoboCup-2001, Seattle, USA, August 2 10, 2001 Advisory Committee: IJCAI-03 Senior Program Committee: IJCAI-01, AAMAS-02, AAAI-01, Agents-01, AAAI-00, Agents-00, AAAI-99 Program Committee: AIPS-02, ECP-01, ICML-00, AIPS-00, EPIA-99, ICML-99, ICCBR-99, IJCAI-99, Agents- 99, Agents-98, ICML-98, AAAI-98, Agents-97, EPIA-97, RoboCup-97, AAAI-97, ICCBR-97, AIPS-94 Worshop Co-Chair: AIPS-02, RoboCup-99 General Organizing Chair: RoboCup-01, First RoboCup American Open 03 General Organizing Co-Chair: RoboCup-98, RoboCup-00 Program Co-Chair: ICCBR-95, AIPS-98 Program Chair: NSF-sponsored workshop on Intelligent Robotic Agents, Brazil, March 1997 Press: Since 1997, interviewed by many national and international reporters and cited in many (more than 50?) publications, including national and international newspapers, magazines, and TV productions, to wit Scientific American Frontiers on Games Machines Play, premiered May 21, 2002 and Natural Born Robots, premiered November 2, (AAAI - American Association of Artificial Intelligence; Agents - International Conference on Agents; AIPS - International Conference on Artificial Intelligence Planning Systems; EPIA - Portuguese Conference on Artificial Intelligence; ICCBR - International Conference on Case-Based Reasoning; ICML - International Conference on Machine Learning; IJCAI - International Joint Conference on Artificial Intelligence.) 3

4 Invited Presentations 2003 November 10, Rice University, Distinguished Lecture. July 12, RoboCup-2003, Keynote Lecture. Robot Soccer: A Fantastic and Challenging Research Pursuit. May 9, Robotica 2003, Keynote Lecture, Lisbon, Portugal. Coordination of Robot Teams in Adversarial Environments. May 7, IRST, Distinguished Lecture, Trento, Italy. Coordination of Teams of Robots. April 3, Snowbird Workshop, Invited lecture, Salt Lake City, UT. Dynamic Multi-Robot Coordination in the Presence of Teammates and Adversaries. February 27, Michigan State University, Annual Distinguished Lecture, Physics Department, East Lansing, MI. Robots that can Collaborate and Learn. January 30, Harvard University. Multi-robot Coordination in Dynamic Environments. January 17, Georgia Institute of Technology, Atlanta, GA. Coordinating Autonomous Robots December The Future of AI Workshop, Tokyo, Japan. Autonomous Robot Soccer Teams. December 12 - AdIn Research, Tokyo, Japan. Autonomous Robot Soccer Teams. December 11 - Sony, Tokyo, Japan. Autonomous Robot Research at Carnegie Mellon. November 8, Mexico Institute for Applied Mathematics and Systems, Autonomous Multi-Robot Team Perception, Action, Execution, and Learning in Adversarial Environments. November 3-5, Darpa IPTO Workshop, Airlie House. Purposeful Perception. October 30, International Lisp Conference, San Francisco. October 24, St. John s University, NYC. Robots as Autonomous Beings with Perception, Cognition, and Action. October 10, Grace Hopper Conference, Vancouver, Canada October 8, National Academy of Engineering. Autonomous Robot Soccer Teams. September 13, CP 02 doctoral programme, Cornell University. To Advise and To Be Advised. September 2, EURON Summer School on Cooperative Robotics, Lisbon, Portugal. Perception, Action Selection, and Learning for Teams of Robots in Adversarial Domains. August 1, HRL, Malibu, CA. Autonomous Multi-Robot Teams. July 27, DarpaTech, Los Angeles, CA. July 9, NIST, host: Larry Reeker, Washington, DC. Autonomous Multi-Robot Teams. July 8, IDA, host: Joe Toth, Washington, DC. Behaviors in Teams of Complete Intelligent Agents. May 7, Carnegie Mellon, AI seminar. Multi-Robot Team Coordination and Learning in Adversarial Environments. May 3, Lehigh University, Distinguished Lecture. Autonomous Multi-Robot Teams. April 24, CNRS, Nice, France. Autonomous Multi-Robot Teams. April 23, AIPS-02, workshop on Exploring Real-World Planning, keynote lecture, Toulouse. Autonomous Multi-Robot Teams. April 7, Carnegie Science Center, Pittsburgh. April 3, Columbia University, NY. Teams of Autonomous Robots. March 12, Goddard Space Flight Center, NASA, Maryland. Autonomous Multi-Robot Teams. Jan 10, Agents School, ISI/USC. Perception, Action Selection, and Learning for Teams of Robots in Adversarial Domains October 22, Harvard University, Science and the Spiritual Quest, Embodied and Social: Robotics Building Upon and Contributing to What We know About Human Being and Intelligence. 4

5 August 9, IJCAI-01, Invited Talk, Seattle, The Challenges and Advances in Teams of Autonomous Agents in Adversarial Environments. July 31, ICCBR-01, Invited Talk, International Conference on Case-Based Reasoning, Vancouver, Building and Using Experience in Multiagent Systems. July 17, AT&T Research, Florham Park, NJ, Multiagent Learning: Towards Learning to Model and Respond to Adversaries. Host: Ron Brachman. May 25, Science and the Spiritual Quest, Unesco, Paris, Robots - Creatures Without a Soul? May 21, Harvard University, Cambridge, Multirobot Perception and Learning, AI class, Avi Pfeffer March 28, International Symposium on Distributed Autonomous Robots, Dallas, Panel on Robotics in Education and Entertainment, Advances in Multi-Robot Systems through RoboCup. February 14-15, AAAS Seminar on Genomics, Robotics and Nanotechnology, AAAS Annual Meeting, including response to Bill Joy, Teams of Intelligent Robots. February 3, Westinghouse Science Honors Institute, Pittsburgh. Teams of Autonomous Robotic Agents December Science and the Spiritual Quest II, New York, Autonomous Robots with Perception, Cognition, and Action. July 30, AAAI-2000, Mentoring Plenary Tutorial, on Advising Graduate Students. June 6, University of Girona, Girona, Spain. Learning in Agents that Plan and Execute. June 5, Agents-2000, Invited Talk, Barcelona, Spain. Perception, Action, and Learning in Teams of Autonomous Agents. May 16, Association of Portuguese MIT Students. Planning, Execution, and Learning in Teams of Autonomous Agents. April 10, Harvard University. Planning, Execution, and Learning in Teams of Autonomous Agents. April 7, BBN Technologies. Teams of Autonomous Agents: Action, Perception, Execution, and Learning. March 6, Oregon State University. Planning, Execution, and Learning in Teams of Autonomous Agents. March 1, Draper Labs. Planning, Execution, and Learning in Teams of Autonomous Agents. February 26, Millennium Celebrations, Portugal Multiagent Software and Robotic Systems. February 10, MIT AI Colloquium. Planning, Execution, and Learning in Teams of Autonomous Agents December 20, Faculdade de Ciências, Lisbon. Multiagent Teams of Robotic Soccer: Simulation, Small Wheeled Robots, and Autonomous Legged Robots. December 10, Smithsonian Museum, Washington, DC. General public presentations and robot demonstrations. December 3, Yale University, New Haven. Action, Perception, and Goal Achievement in Teams of Autonomous Robotic Soccer Agents. November 2, MIT Lincoln Lab. Integrating Information, Planning, and Execution Agents. October 30, Carnegie Mellon University, Keynote speaker, Westinghouse Science Awards Dinner, Multi-Agent Planning, Execution, and Learning. April 23, The New England Symposium on Reinforcement Learning, University of Massachusetts, Amherst. What to do next?: Action selection in dynamic multi-agent environments. February 26, Pittsburgh Super Computing Center, Pittsburgh. Towards Learning to Map Signal Processing Algorithms, Implementations, Compilers, and Machines. February 13, Westinghouse Science Honors Institute, Pittsburgh. Goal Achievement in Teams of 5

6 Autonomous Robotic Agents November 13, Cornell University, AI seminar. Perception, Action, and Planning in Teams of Autonomous Robotic Agents. November 6, University of Pennsylvania, GRASP seminar. Perception, Action, and Planning in Teams of Autonomous Robotic Agents. October 22-30, Visit to RMIT (Royal Melbourne Institute of Technology), and Interact, Melbourne, Australia. Teams of Robotic Soccer Agents: Autonomous Legged Robots. October 1, Invited speaker at AI*IA-98, (Association of Italian Artificial Intelligence), Workshop on New Trends in Robotics, Padova, Italy. Teams of Robotic Soccer Agents: Simulation, Globally Controlled Wheeled Robots, and Autonomous Legged Robots. September 27, IRST, Trento, Italy. Teams of Robotic Soccer Agents: Simulation, Globally Controlled Wheeled Robots, and Autonomous Legged Robots. September 22, Invited speaker at AIMSA 98, the 8th International Conference on AI: Methodology, Systems, Applications, Sozopol, Bulgaria. Teams of Robotic Soccer Agents: Simulation, Globally Controlled Wheeled Robots, and Autonomous Legged Robots. August 19, Dartmouth University. Teams of Robotic Soccer Agents: Simulation, Globally Controlled Wheeled Robots, and Autonomous Legged Robots. June 1, Smithsonian Museum, Washington, DC. Teams of Intelligent Robotic Agents. March 20, Carnegie Mellon University, Speaker of Honor for Women in Science and Engineering. Strategy, Collaboration and Learning in Teams of Autonomous Agents. January 10, 1998 Westinghouse Science Honors. Teams of Autonomous Robotic Agents October 28, Carnegie Mellon University, Freshmen Immigration Course, Computer Science Department. Collaboration and Learning in Autonomous Intelligent Agents. October 24, Carnegie Mellon University, University Family Weekend. Collaboration and Learning in Autonomous Intelligent Agents. October 8, 1997 Instituto de Sistemas e Robótica, Instituto Superior Técnico, Lisbon, Portugal. Towards Continuous Planning, Execution, and Learning in MultiAgent Systems: A Team of Robotic Soccer Agents. October 7, 1997 Workshop on Multiagent Systems, EPIA-97, Portugal. Towards Continuous Planning, Execution, and Learning in MultiAgent Systems: A Team of Robotic Soccer Agents. September 30, 1997 Advanced Mechatronics Lab Seminar, Carnegie Mellon University. Towards Continuous Planning, Execution, and Learning in MultiAgent Systems: A Team of Robotic Soccer Agents. September 30, 1997 Carnegie Mellon University, AI seminar. Towards Continuous Planning, Execution, and Learning in MultiAgent Systems: A Team of Robotic Soccer Agents. September 3, 1997 ETL, Japan. Towards Continuous Planning, Execution, and Learning in MultiAgent Systems: A Team of Robotic Soccer Agents. February 10th, 1997 Information Sciences Institute, University of Southern California, Marina del Rey, CA. Using Analogical Plan Replay in Conditional, Mixed-Initiative, and Multiagent Planning. January 18, 1997 Westinghouse Science Honors, Pittsburgh. Computers that Think and Learn December 3, 1996 Carnegie Mellon University, AI seminar. Towards Collaborative Planning. November 1996 Dagstuhl, Germany, seminar series on Control of Search in AI planning. October 22, 1996 Freshmen Immigration Course, Computer Science Department, Carnegie Mellon University. What is Artificial Intelligence? October 7, 1996 University of Chicago, Department of Computer Science. Learning and Orchestration in Multi-agent and Multi-task Systems. October 5, 1996 Carnegie Mellon University, The Herstories retreat on Culture Crossing. 6

7 October 3, 1996 Carnegie Group, Inc., Pittsburgh, Machine Learning in Planning. April 19, 1996 National Portuguese Television, RTP2, Lisbon, Portugal. First show of a new TV series on scientific themes, title of the show: Rumo à Lua (Towards the Moon). Interviewed by C. Correia on the theme of Robotics, Machine Intelligence, and the Biological Similarity to Insects. March 4, 1996 Carnegie Mellon University, High School Day, organized by the Society of Women Engineers. Computer Science: Exciting today and in the future. January 22, 1996 Naval Research Laboratory, Washington, DC. Towards Experience-Based Agents that Plan, Act, and Perceive December 20, 1995 University of Aveiro, Portugal. Einstein and Edison: Compromise in University Research November 30, 1995 MIT AI Lab. Towards Experience-Based Agents that Plan, Act, and Perceive. October 4, 1995 Invited talk at EPIA-95, the Seventh Portuguese Conference on Artificial Intelligence, Madeira, Portugal. Agents that Plan and Learn. August 30, 1995 ARPA Sisto Symposium. Planning by Retrieving and Merging Planning Cases June 29 - July 9, 1994 University of Kaiserslautern, Germany. Comparison of Planning Algorithms. July 6, 1994 University of Saarbrücken, Germany. Machine Learning in Problem Solving. June 1994 Invited chair of the panel on Planning and Learning at the Second International Conference on Planning Systems. May 15-20, University of São Paulo, Brazil. Course on Planning and Learning November 1993 Invited keynote speaker at the First European Workshop on Case-Based Reasoning, Kaiserslautern, Germany. Analogical/Case-Based Reasoning in General Problem Solving. November 8, 1993 University of Kaiserslautern, Germany. Learning by Analogical Reasoning in General Problem Solving. May 4, 1993 Faculty of Economy, Lisbon, Portugal. Academics and Research: A Ph.D. graduating experience at Carnegie Mellon. February 1993 Selected presentation at the 1993 DARPA Workshop on Planning. Acquiring Planning Expertise by Analogical Reasoning October 14, University of Chicago, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. May 1, Mitsubishi Research, Cambridge, Learning by Analogical Reasoning in General Problem Solving. April 30, Johns Hopkins University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 29, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 27, Purdue University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 22, University of Massachusetts, Amherst, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 20, Carnegie Mellon University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 15, Columbia University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 13, University of Pittsburgh, Department of Information Science. Learning by Analogical 7

8 Reasoning in General Problem Solving. April 10, Boston University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. April 8, AT&T Research, Learning by Analogical Reasoning in General Problem Solving. April 1, NEC, Learning by Analogical Reasoning in General Problem Solving. March 20, Information Sciences Institute, Learning by Analogical Reasoning in General Problem Solving. March 16, Institute for the Learning Sciences, Northwestern University. Learning by Analogical Reasoning in General Problem Solving. March 12, Oregon State University, Department of Computer Science. Learning by Analogical Reasoning in General Problem Solving. List of Publications Books 1. M. Veloso, E. Pagello, and H. Kitano, editors. RoboCup-99: Robot Soccer World Cup III. Springer-Verlag Press, Berlin, August Michael Wooldridge and Manuela Veloso, editors. Artificial Intelligence Today: Recent Trends and Developments. Springer, Katsu Ikeuchi and Manuela Veloso, editors. Symbolic Visual Learning. Oxford University Press, March Manuela Veloso and Agnar Aamodt, editors. Case-Based Reasoning Research and Development. Springer Verlag, October Manuela M. Veloso. Planning and Learning by Analogical Reasoning. Springer Verlag, December Book Chapters 6. William Uther and Manuela Veloso. TTree: Tree-Based State Generalization with Temporally Abstract Actions. In Adaptive Agents and Multi-Agent Systems, volume LNAI 2636, pages Springer, Rune Jensen, Michael Bowling, and Manuela Veloso. Multiagent planning in the presence of multiple goals. In Intelligent Planning. John Wiley, 2003, forthcoming. 8. Douglas Vail and Manuela Veloso. Dynamic multi-robot coordination. In Multi-Robot Systems: From Swarms to Intelligent Automata, Volume II, pages Kluwer Academic Publishers, Manuela Veloso. Robot soccer: A Multi-Robot challenge. In Multi-Robot Systems: From Swarms to Intelligent Automata. Kluwer, James Bruce, Scott Lenser, and Manuela Veloso. Fast walking for legged robots. In A. Birk, S. Coradeschi, and S. Tadokoro, editors, RoboCup-2001: The Fifth RoboCup Competitions and Conferences. Springer Verlag, Berlin, Scott Lenser, James Bruce, and Manuela Veloso. A modular hierarchical behavior-based architecture. In A. Birk, S. Coradeschi, and S. Tadokoro, editors, RoboCup-2001: The Fifth RoboCup Competitions and Conferences. Springer Verlag, Berlin, Patrick Riley and Manuela Veloso. Adaptive team-adversarial coaching. In A. Birk, S. Coradeschi, and S. Tadokoro, editors, RoboCup-2001: The Fifth RoboCup Competitions and Conferences. Springer Verlag, Berlin, Scott Lenser, James Bruce, and Manuela Veloso. CM-Pack 00. In P. Stone, T. Balch, and G. Kraetzschmar, editors, RoboCup-2000: Robot Soccer World Cup IV, pages Springer Verlag, Berlin,

9 14. Patrick Riley, Peter Stone, David McAllester, and Manuela Veloso. ATT-CMUnited-2000: Third place finisher in the RoboCup-2000 simulator league. In P. Stone, T. Balch, and G. Kraetzschmar, editors, RoboCup-2000: Robot Soccer World Cup IV, pages Springer Verlag, Berlin, Manuela Veloso, Hiroaki Kitano, Enrico Pagello, Gerhard Kraetzschmar, Peter Stone, Tucker Balch, Minoru Asada, Silvia Coradeschi, Lars Karlsson, and Masahiro Fujita. Overview of RoboCup-99. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Peter Stone, Patrick Riley, and Manuela Veloso. The CMUnited-99 champion simulator team. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Michael Bowling and Manuela Veloso. Motion control in dynamic multi-robot environments. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Peter Stone and Manuela Veloso. Layered learning and flexible teamwork in RoboCup simulation agents. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Manuela Veloso, Michael Bowling, and Sorin Achim. CMUnited-99: Small-size robot team. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Manuela Veloso, Scott Lenser, Elly Winner, and James Bruce. CM-Trio-99. In M. Veloso, E. Pagello, and H. Kitano, editors, RoboCup-99: Robot Soccer World Cup III, pages Springer Verlag, Berlin, Peter Stone and Manuela Veloso. Task decomposition and dynamic role assignment for real-time strategic teamwork. In J. P. Müller, M. P. Singh, and A. S. Rao, editors, Intelligent Agents V Proceedings of the Fifth International Workshop on Agent Theories, Architectures, and Languages (ATAL-98), volume 1555 of Lecture Notes in Artificial Intelligence, pages Springer-Verlag, Heidelberg, Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, and Peter Stone. The CMUnited-98 champion small robot team. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, pages Springer Verlag, Berlin, Manuela Veloso and William Uther. The CMTrio-98 Sony legged robot team. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, pages Springer Verlag, Berlin, Peter Stone, Manuela Veloso, and Patrick Riley. The CMUnited-98 champion simulator team. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, pages Springer Verlag, Berlin, Peter Stone and Manuela Veloso. Team-partitioned, opaque-transition reinforcement learning. In Minoru Asada and Hiroaki Kitano, editors, RoboCup-98: Robot Soccer World Cup II, pages Springer Verlag, Berlin, Peter Stone and Manuela Veloso. Communication in domains with unreliable, single-channel, low-bandwidth communication. In Alexis Drogoul, Milind Tambe, and Toshio Fukuda, editors, Collective Robotics, pages Springer Verlag, Berlin, July Peter Stone and Manuela Veloso. Using decision tree confidence factors for multiagent control. In Hiroaki Kitano, editor, RoboCup-97: The First Robot World Cup Soccer Games and Conferences, pages Springer Verlag, Berlin, Peter Stone and Manuela Veloso. The CMUnited 97 simulator team. In Hiroaki Kitano, editor, RoboCup-97: The First Robot World Cup Soccer Games and Conferences, pages Springer Verlag, Berlin,

10 29. Manuela Veloso, Peter Stone, Kwun Han, and Sorin Achim. CMUnited: A team of robotic soccer agents collaborating in an adversarial environment. In Hiroaki Kitano, editor, RoboCup-97: The First Robot World Cup Soccer Games and Conferences, pages Springer Verlag, Berlin, Astro Teller and Manuela M. Veloso. PADO: A new learning architecture for object recognition. In K. Ikeuchi and M. Veloso, editors, Symbolic Vision and Learning, pages Oxford Press, Manuela M. Veloso. Flexible strategy learning: Analogical replay of problem solving episodes. In David B. Leake, editor, Case-Based Reasoning: experiences, lessons, and future directions, pages AAAI Press/The MIT Press, May Book printing of the paper presented at AAAI-94, the Twelfth National Conference on Artificial Intelligence, AAAI Press, Manuela M. Veloso. Towards mixed-initiative rationale-supported planning. In A. Tate, editor, Advanced Planning Technology, pages AAAI Press, May Peter Stone and Manuela M. Veloso. User-guided interleaving of planning and execution. In New Directions in AI Planning, pages IOS Press, Eugene Fink and Manuela M. Veloso. Formalizing the PRODIGY planning algorithm. In New Directions in AI Planning, pages IOS Press, An earlier extended version is available as technical report CMU-CS , Manuela M. Veloso. Prodigy/Analogy: Analogical reasoning in general problem solving. In S. Wess, K.-D. Althoff, and M. Richter, editors, Topics in Case-Based Reasoning, pages Springer Verlag, Manuela M. Veloso and Jaime G. Carbonell. Case-based reasoning in PRODIGY. In R. S. Michalski and G. Teccuci, editors, Machine Learning: A Multistrategy Approach, Volume IV, pages Morgan Kaufmann, Manuela M. Veloso and Jaime G. Carbonell. Towards scaling up machine learning: A case study with derivational analogy in PRODIGY. In S. Minton, editor, Machine Learning Methods for Planning, pages Morgan Kaufmann, Manuela M. Veloso and Jaime G. Carbonell. Integrating analogy into a general problem-solving architecture. In Maria Zemankova and Zbigniew Ras, editors, Intelligent Systems, pages Ellis Horwood, Chichester, England, Journal Articles 39. Brett Browning, James Bruce, Michael Bowling, and Manuela Veloso. Multiple control levels in fast soccer robots. IMechE, Journal of Systems and Control Engineering, 2003, for submission. 40. Patrick Riley and Manuela Veloso. Planning for distributed team execution using probabilistic opponent models. Journal of Artificial Intelligence Research, 2003, for submission. 41. Michael Bowling and Manuela Veloso. Existence of multiagent equilibria with limited agents. Journal of Artificial Intelligence Research, 2003, under revision. 42. Michael Bowling and Manuela Veloso. Multiagent learning using a variable learning rate. Artificial Intelligence, 136: , Bryan Singer and Manuela Veloso. Automating the modeling and optimization of the performance of signal transforms. IEEE Transactions on Signal Processing, 2002, in press. 44. Bryan Singer and Manuela Veloso. Learning to construct fast signal processing implementations. Journal of Machine Learning Research, 3: , G. A. Kaminka, M. M. Veloso, S. Schaffer, C. Sollitto, R. Adobbati, A. N. Marshal, A. Scholer, and S. Tejada. GameBots: The ever-challenging multi-agent research test-bed. Communications of the ACM, January

11 46. Astro Teller and Manuela Veloso. Internal reinforcement in a connectionist genetic programming approach. Artificial Intelligence, 120/2, July Peter Stone and Manuela Veloso. Multiagent systems: A survey from a machine learning perspective. Autonomous Robots, 8(3): , Rune M. Jensen and Manuela M. Veloso. OBDD-based universal planning for synchronized agents in nondeterministic domains. Journal of Artificial Intelligence Research, 13: , July Peter Stone and Manuela Veloso. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Artificial Intelligence, 110(2): , June Minoru Asada, Hiroaki Kitano, Itsuki Noda, and Manuela Veloso. RoboCup: Today and tomorrow What we have have learned. Artificial Intelligence, 110: , Manuela Veloso, Peter Stone, and Kwun Han. The CMUnited-97 robotic soccer team: Perception and multiagent control. Robotics and Autonomous Systems, 29 (2-3): , Karen Zita Haigh and Manuela M. Veloso. Learning situation-dependent costs: Improving planning from probabilistic robot execution. Robotics and Autonomous Systems, 29 (2-3): , Peter Stone and Manuela Veloso. A layered approach to learning client behaviors in the RoboCup soccer server. Applied Artificial Intelligence, 12: , Peter Stone and Manuela Veloso. Towards collaborative and adversarial learning: A case study in robotic soccer. International Journal of Human-Computer Systems, 48, Karen Zita Haigh and Manuela M. Veloso. Interleaving planning and robot execution for asynchronous user requests. Autonomous Robots, 5(1):79 95, March Paola Rizzo, Manuela Veloso, Maria Miceli, and Amedeo Cesta. Goal-based personalities and social behaviors in believable agents. Applied Artificial Intelligence, 13: , Karen Z. Haigh, Jonathan Shewchuk, and Manuela M. Veloso. Exploring geometry in analogical route planning. Journal of Experimental and Theoretical Artificial Intelligence, 9: , Yury Smirnov, Sven Koenig, and Manuela M. Veloso. Heuristic-driven treasure hunt with linear performance guarantees. Congress Numerantium Journal, 117: , Manuela M. Veloso, Héctor Munoz-Avila, and Ralph Bergmann. General-purpose case-based planning: Methods and systems. AI Communications, 9(3): , Also in Künstliche Intelligenz, 1:22-28, 1996, in German (with reversed order of the authors).). 60. Daniel Borrajo and Manuela Veloso. Lazy incremental learning of control knowledge for efficiently obtaining quality plans. AI Review Journal. Special Issue on Lazy Learning, 10:1 34, Astro Teller and Manuela M. Veloso. Program evolution for data mining. International Journal of Expert Systems, 8(3): , Manuela M. Veloso and Peter Stone. FLECS: Planning with a flexible commitment strategy. Journal of Artificial Intelligence Research, 3:25 52, Manuela M. Veloso, Jaime Carbonell, M. Alicia Pérez, Daniel Borrajo, Eugene Fink, and Jim Blythe. Integrating planning and learning: The PRODIGY architecture. Journal of Experimental and Theoretical Artificial Intelligence, 7(1):81 120, Manuela M. Veloso and Jaime G. Carbonell. Derivational analogy in PRODIGY: Automating case acquisition, storage, and utilization. Machine Learning, 10: ,

12 Magazine Articles 65. Manuela Veloso. Autonomous robot soccer teams. The Bridge, National Academy of Engineering, 33(1):8 12, Spring P. Lima, T. Balch, M. Fujita, R. Rojas, M. Veloso, and H. Yanco. Robocup IEEE Robotics and Automation Magazine, 9(2):20 30, June Manuela Veloso, Tucker Balch, Peter Stone, and Hiroaki Kitano. Overview of RoboCup AI Magazine, Spring Minoru Asada, Manuela Veloso, Milind Tambe, Itsuki Noda, Hiroaki Kitano, and Gerhard Kraetzschmar. Overview of RoboCup-98. AI Magazine, 21(1):9 19, Spring Peter Stone, Manuela Veloso, and Patrick Riley. CMUnited-98: RoboCup-98 simulator world champion team. AI Magazine, 21(1):20 28, Spring Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, and Peter Stone. CMUnited-98: RoboCup-98 small-robot world champion team. AI Magazine, 21(1):29 36, Spring Masahiro Fujita, Manuela Veloso, William Uther, Minoru Asada, Hiroaki Kitanon, Vincent Hugel, Patrick Bonnin, Jean-Christophe Bouramoué, and Pierre Blazevic. Vision, strategy, and localization using the Sony legged robots at RoboCup-98. AI Magazine, 21(1):47 56, Spring Manuela Veloso, William Uther, and Masahiro Fujita. Walking soccer-playing robots. Robot Science and Technology Magazine, November Manuela Veloso, Peter Stone, and Kwun Han. CMUnited-97: RoboCup-97 small-robot world champion team. AI Magazine, 19(3):61 69, Manuela Veloso, Peter Stone, Kwun Han, and Sorin Achim. CMUnited: A team of robotic soccer agents collaborating in an adversarial environment. Crossroads, 4.3, February Conference Papers 75. Scott Lenser and Manuela Veloso. Visual sonar: Fast obstacle avoidance using monocular vision. In Proceedings of IROS 03, Las Vegas, October Maayan Roth, Douglas Vail, and Manuela Veloso. A world model for multi-robot teams with communication. In Proceedings of IROS 03, October Elly Winner and Manuela Veloso. DISTILL: Towards learning domain-specific planners by example. In Proceedings of ICML 03, Washington, DC, August Michael Bowling and Manuela Veloso. Simultaneous adversarial multi-robot learning. In Proceedings of IJ- CAI 03, Acapulco, Mexico, August Michael Bowling, Rune Jensen, and Manuela Veloso. A formalization of equilibria for multiagent planning. In Proceedings of IJCAI 03, Acapulco, Mexico, August Michael Bowling, Brett Browning, Allen Chang, and Manuela Veloso. Plays as team plans for coordination and adaptation. In Proceedings of the RoboCup 03 Symposium, Padua, Italy, July Patrick Riley and Manuela Veloso. Coaching advice and adaptation. In Proceedings of AAMAS 03, Melbourne, Australia, July Thuc Vu, Jared Go, Gal Kaminka, Manuela Veloso, and Brett Browning. MONAD: A flexible architecture for multi-agent control. In Proceedings of AAMAS 03, Melbourne, Australia, July Rune Jensen, Manuela Veloso, and Randy Bryant. Guided symbolic universal planning. In Proceedings of ICAPS 03, Trento, Italy, June

13 84. Rune M. Jensen, Manuela M. Veloso, and Randy E. Bryant. Synthesis of fault-tolerant plans for nondeterministic domains. In Proceedings of the ICAPS 03 Workshop on Planning under Uncertainty and Incomplete Information, Trento, Italy, June James Bruce and Manuela Veloso. Fast and accurate vision-based pattern detection and identification. In Proceedings of ICRA 03, the 2003 IEEE International Conference on Robotics and Automation, Taiwan, May Scott Lenser and Manuela Veloso. Automatic detection and response to environmental change. In Proceedings of ICRA 03, the 2003 IEEE International Conference on Robotics and Automation, Taiwan, May James Bruce, Michael Bowling, Brett Browning, and Manuela Veloso. Multi-robot team response to a multirobot opponent team. In Proceedings of ICRA 03, the 2003 IEEE International Conference on Robotics and Automation, Taiwan, May James Bruce and Manuela Veloso. Real-time randomized path planning for robot navigation. In Proceedings of IROS-2002, Switzerland, October An earlier version of this paper appears in the Proceedings of the RoboCup-2002 Symposium. 89. Rune M. Jensen, Randy E. Bryant, and Manuela M. Veloso. SetA*: An efficient BDD-based heuristic search algorithm. In Proceedings of AAAI-2002, Edmonton, Canada, August Michael Bowling, Rune Jensen, and Manuela Veloso. A formalization of equilibria for multiagent planning. In Proceedings of the AAAI-2002 Workshop on Multiagent Planning, Edmonton, Canada, August Michael Bowling and Manuela Veloso. Scalable learning in stochastic games. In Proceedings of the AAAI-2002 Workshop on Game Theoretic and Decision Theoretic Agents, Edmonton, Canada, August William Uther and Manuela Veloso. TTree: Tree-based state generalization with temporally abstract actions. In Proceedings of SARA-2002, Edmonton, Canada, August Patrick Riley, Manuela Veloso, and Gal Kaminka. Any team coaching. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy, July Paul Carpenter, Patrick Riley, Manuela Veloso, and Gal Kaminka. Integration of advice in an action-selection architecture. In Proceedings of the RoboCup-2002 Symposium, Fukuoka, Japan, June Gal Kaminka, Mehmet Fidanboylu, Allen Chang, and Manuela Veloso. Learning the sequential coordinated behavior of teams from observations. In Proceedings of the RoboCup-2002 Symposium, Fukuoka, Japan, June Patrick Riley, Manuela Veloso, and Gal Kaminka. An empirical study of coaching. In Proceedings of DARS- 2002, the Seventh International Symposium on Distributed Autonomous Robotic Systems, Fukuoka, Japan, June Brett Browning, Gal Kaminka, and Manuela Veloso. Principled monitoring of distributed agents for detection of coordination failure. In Proceedings of DARS-2002, the Seventh International Symposium on Distributed Autonomous Robotic Systems, Fukuoka, Japan, June Brett Browning, Michael Bowling, and Manuela Veloso. Improbability filtering for rejecting false positives. In Proceedings of 2002 IEEE International Conference on Robotics and Automation, Washington, DC, May Patrick Riley and Manuela Veloso. Planning for distributed execution through use of probabilistic opponent models. In Proceedings of the Sixth International Conference on Artificial Intelligence Planning Systems, Best Paper Award, Toulouse, France, April Elly Winner and Manuela Veloso. Analyzing plans with conditional effects. In Proceedings of the Sixth International Conference on Artificial Intelligence Planning Systems, Toulouse, France, April

14 101. Laurie Hiyakumoto and Manuela Veloso. Towards planning and execution for information retrieval. In Proceedings of AIPS 02 Workshop on Exploring Real-World Planning, Toulouse, April Rune M. Jensen, Randy E. Bryant, and Manuela M. Veloso. An efficient BDD-based A* algorithm. In Proceedings of AIPS 02 Workshop on Planning via Model Checking, Toulouse, April Elly Winner and Manuela Veloso. Automatically acquiring planning templates from example plans. In Proceedings of AIPS 02 Workshop on Exploring Real-World Planning, Toulouse, April Bryan Singer and Manuela M. Veloso. Stochastic search for signal processing algorithm optimization. In Proceedings of SC Scientific Computing 2001, Denver, Colorado, November Rune Jensen, Manuela Veloso, and Michael Bowling. Optimistic and strong cyclic adversarial planning. In Proceedings of ECP-2001, European Conference on Planning, Toledo, Spain, October Michael Bowling and Manuela Veloso. Rational learning of mixed equilibria in stochastic games. In Proceedings of IJCAI-2001, (selected paper for submission to Artificial Intelligence), August Michael Bowling and Manuela Veloso. Convergence of gradient dynamics with a variable learning rate. In Proceedings of ICML-2001, pages 27 34, Williams College, MA, June Bryan Singer and Manuela Veloso. Learning to generate fast signal processing implementations. In Proceedings of ICML-2001, pages , Williams College, MA, June Tucker Balch, Zia Kahn, and Manuela Veloso. Observing ants: Tracking and analyzing the behavior of live ant colonies. In Proceedings of the Fifth International Conference on Autonomous Agents, May Scott Lenser, James Bruce, and Manuela Veloso. CMPack: A complete software system for autonomous legged soccer robots. In Proceedings of the Fifth International Conference on Autonomous Agents, May Best Paper Award in the Software Prototypes Track, Honorable Mention Patrick Riley and Manuela Veloso. Adaptive team coaching using opponent model selection. In Proceedings of the Fifth International Conference on Autonomous Agents, May Markus Püschel, Bryan Singer, Manuela Veloso, and José M.F. Moura. Fast automatic generation of dsp algorithms. In Proceedings of the Special Session on Architecture-Specific Automatic Performance Tuning at the International Conference on Computational Science, April Minoru Asada, Andreas Birk, Enrico Pagello, Masahiro Fujita, Itsuki Noda, Satoshi Tadokoro, Dominique Duhaut, Peter Stone, Manuela Veloso, Tucker Balch, Hiroaki Kitano, and B. Thomas. Progress in RoboCup soccer research in In Proceedings of the 2000 International Symposium on Experimental Robotics, October James Bruce, Tucker Balch, and Manuela Veloso. Fast and inexpensive color image segmentation for interactive robots. In Proceedings of IROS-2000, Japan, October Patrick Riley and Manuela Veloso. On behavior classification in adversarial environments. In Proceedings of DARS-00, the Fifth International Symposium on Distributed Autonomous Robotic Systems, October Elly Winner and Manuela Veloso. Multi-fidelity behaviors: Acting with variable state information. In Proceedings of AAAI-00, August Patrick Riley and Manuela Veloso. Towards behavior classification: A case study in robotic soccer. In Proceedings of AAAI-00 (student abstract), August Peter Stone, Patrick Riley, and Manuela Veloso. Defining and using ideal teammate and opponent agent models. In Proceedings of the Twelfth Annual Conference on Innovative Applications of Artificial Intelligence, (IAAI- 00), August

15 119. William Uther and Manuela Veloso. The Lumberjack algorithm for learning linked decision forests. In Proceedings of PRICAI-2000, August A longer version of this paper is in Proceedings of the Symposium on Abstraction, Reformulation and Approximation (SARA-00), July 2000, Texas Patrick Riley, Peter Stone, and Manuela Veloso. Layered disclosure: Revealing agents internals. In Proceedings of Agents, Theories, and Architectures (ATAL-00), Boston, July Bryan Singer and Manuela Veloso. Learning to predict performance from formula modeling and training data. In Proceedings of the Seventeenth International Conference on Machine Learning (ICML-00), July Astro Teller and Manuela Veloso. Efficient learning through evolution: Neural programming and internal reinforcement. In Proceedings of the Seventeenth International Conference on Machine Learning (ICML-00), July Peter Stone, Patrick Riley, and Manuela Veloso. Why is the agent doing what it s doing? In Proceedings of the Fourth International Conference on Autonomous Agents (Agents-00), Barcelona, June Manuela Veloso, Tucker Balch, and Scott Lenser. Integrating information agents, planning, and execution monitoring. In Proceedings of the Fourth International Conference on Autonomous Agents (Agents-00), Barcelona, June Peter Stone and Manuela Veloso. Layered learning. In Proceedings of the European Conference on Machine Learning, ECML-2000, June Scott Lenser and Manuela Veloso. Sensor resetting localization for poorly modelled mobile robots. In Proceedings of ICRA-2000, the International Conference on Robotics and Automation, San Francisco, CA, April Rune Jensen and Manuela Veloso. OBDD-based universal planning for multiple synchronized agents in nondeterministic domains. In Proceedings of the Fifth International Conference on Artificial Intelligence Planning Systems (AIPS-00), Breckenridge, CO, April Manuela Veloso, Elly Winner, Scott Lenser, James Bruce, and Tucker Balch. Vision-servoed localization and behavior-based planning for an autonomous quadruped legged robot. In Proceedings of the Fifth International Conference on Artificial Intelligence Planning Systems (AIPS-00), Breckenridge, CO, April Rune Jensen and Manuela Veloso. The UMOP planning framework: Results in classical deterministic domains. In Proceedings of the AIPS-2000 Worskhop on Model Checking Planning, Breckenridge, CO, April Michael Bowling and Manuela Veloso. Motion control in dynamic multi-robot environments. In Proceedings of The 1999 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA 99), Monterey, November Kwun Han and Manuela Veloso. Automated robot behavior recognition applied to robotic soccer. In Proceedings of the 9th International Symposium of Robotics Research (ISRR-99), pages , Snowbird, Utah, October Also in Proceedings of IJCAI-99 Workshop on Team Behaviors and Plan Recognition Manuela Veloso, Peter Stone, and Michael Bowling. Anticipation as a key for collaboration in a team of agents: A case study in robotic soccer. In Proceedings of SPIE Sensor Fusion and Decentralized Control in Robotic Systems II, volume 3839, Boston, September Michael Bowling and Manuela Veloso. Bounding the suboptimality of reusing subproblems. In Proceedings of IJCAI-99, August Manuela Veloso, Michael Bowling, Sorin Achim, Kwun Han, and Peter Stone. CMUnited-98: A team of robotic soccer agents. In Proceedings of the Eleventh Annual Conference on Innovative Applications of Artificial Intelligence, (IAAI-99), July Peter Stone and Manuela Veloso. Team partitioned, opaque transition reinforcement learning. In Proceedings of the Third International Conference on Autonomous Agents, pages , July