CS344M: Autonomous Multiagent Systems -- Spring 2008: Resources Page

Resources for Autonomous Multiagent Systems (cs344M)


Week 1: Introduction

  • Initial and final slides from Tuesday: (pdf). The slides on RoboCup.
  • Austin Villa robot soccer team with some links to videos from previous competitions such as the a game from RoboCup 2004.
  • RoboCup 2007 Humanoid league finals.

  • Week 2: Autonomous agents

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf).
  • synthetic challenge paper citeseer site (with reference counts)
  • Similar Google scholar page

  • Week 3: Agent architectures

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf). The ones on planning.
  • A journal article with more details on the initial subsumption implementation:
    Brooks, R. A. "A Robust Layered Control System for a Mobile Robot", IEEE Journal of Robotics and Automation, Vol. 2, No. 1, March 1986, pp. 1423; also MIT AI Memo 864, September 1985.
  • Pengo
  • Structured Control for Autonomous Robots.
    Reid Simmons.
    IEEE Transactions on Robotics and Automation, 10:1, pp. 34-43, February 1994.

  • Week 4: Multiagent systems

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf). The ones on the pursuit domain(ps).
  • The RETSINA agent architecture from CMU.
  • Kevin Murphy's introduction to Bayes rule

  • Week 5: Agent communication and Teamwork

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf).
  • Additional readings on communication:
  • Textbook: chapter 8
    **OR**
    Sections 2.1 and 2.2 (pages 1-19) of Multiagent Systems and Societies of Agents. (get cached copy from upper right corner)
    Michael N. Huhns and Larry M. Stephens.
    Chapter 2 in Multiagent Systems, G. Weiss (ed.), MIT Press, 1998.
  • Desiderata for Agent Communication Languages.
    James Mayfield, Yannis Labrou, and Tim Finin.
    Proceedings of the AAAI Symposium on Information Gathering from Heterogeneous, Distributed Environments, AAAI-95 Spring Symposium, Stanford University, Stanford, CA. March 27-29, 1995.
  • Additional readings on teamwork:
  • Towards Flexible Teamwork.
    Tambe, M.
    Journal of Artificial Intelligence Research (JAIR), Volume 7, pages 83-124, 1997.
  • Regarding ontologies, Cyc and its open-source version, OpenCyc.
  • The Suggested Upper Merged Ontology (SUMO).
  • FIPA sample applications
  • FIPA ACL in XML
  • A paper on evoving communication languages: Talking Helps: Evolving Communicating Agents for the Predator-Prey Pursuit Problem by Jim and Giles
  • A paper on an ACL for soccer agents: CommLang: Communication for Coachable Agents by Divan, Riley, and Veloso.
  • Papers from Luc Steels group on language learning:
    Sharp Transition towards Shared Vocabularies in Multi-Agent Systems
    Experiments on the emergence of human Communication
    The Evolution of Communication Systems by Adaptive Agents
    Intelligence with Representation

  • Week 6: RoboCup case studies

  • Slides from Tuesday: (pdf). Some more (on genetic algorithms - from Tom Mitchell's book Machine Learning)
  • Slides from Thursday: (pdf). The ones on an architecture for action selection (ps).
    The ones on coordination graphs (courtesy of Will Rodgers from the 2005 class)
  • A 1999 salon.com article on Darwin United.
  • The undergraduate writing center
  • Reactive Deliberation: An Architecture for Real-time Intelligent Control in Dynamic Environments.
    Michael K. Sahota.
    Proceedings of the Twelfth National Conference on Artificial Intelligence, 1994.
    (From the group that invented robotic soccer: pre-RoboCup)
  • Co-evolving Soccer Softbot Team Coordination with Genetic Programming.
    Sean Luke, Charles Hohn, Jonathan Farris, Gary Jackson, and James Hendler.
    in Kitano (ed.) RoboCup-97: Robot Soccer World Cup I. Springer Verlag, Berlin, 1998
    (1997 evolutionary learning approach)
  • A Role-Based Decision-Mechanism for Teams of Reactive and Coordinating Agents.
    Slivia Coradeschi and Lars Karlsson.
    in Kitano (ed.) RoboCup-97: Robot Soccer World Cup I. Springer Verlag, Berlin, 1998
    (an early, successful approach)
  • AT Humboldt -- Development, Practice and Theory. (get cached copy from upper right corner)
    Hans-Dieter Burkhard, Markus Hannebauer, Jan Wendler.
    in Kitano (ed.) RoboCup-97: Robot Soccer World Cup I. Springer Verlag, Berlin, 1998
    (1997 champion)
  • Behavior Networks for Continuous Domains using Situation-Dependent Motivations.
    Klaus Dorer.
    Proceedings of the 16th International Joint Conference on Artificial Intelligence, 1999.
    (1999 runner-up)
  • The CMUnited-99 Champion Simulator Team.
    Peter Stone, Patrick Riley, and Manuela Veloso.
    in M. Veloso, E. Pagello and H. Kitano (eds.) RoboCup-99: Robot Soccer World Cup III. Springer Verlag, Berlin, 2000.
    (1998, 1999 champion)
  • FC Portugal Team Description: RoboCup 2000 Simulation League Champion.
    Luis Paulo Reis and Nuno Lau.
    in Stone, Balch, Kraetzschmarr (eds.) RoboCup-2000: Robot Soccer World Cup IV. Springer Verlag, Berlin, 2001.
    (2000 champion)
  • Behavior Classification with Self-Organizing Maps.
    M. Wunstel, D. Polani, T. Uthmann, and J. Perl.
    In: P. Stone, T.Balch, and G. Ktaetzschmar (eds.): RoboCup 2000: Robot Soccer World Cup IV. Berlin, Heidelberg, New York (Springer-Verlag), pages 108-118, 2000. (Lecture Notes in computer science Vol. 2019: Lecture notes in artificial intelligence)
  • Learning Situation Dependent Success Rates of Actions in a RoboCup Scenario.
    Sebastian Buck, Martin Riedmiller.
    Pacific Rim International Coference on Artificial Intelligence, 2000.
    (2000 and 2001 runner-up)
  • Using Machine Learning Techniques in Complex Multi-Agent Domains.
    Martin Riedmiller, Artur Merke
    in I. Stamatescu, W. Menzel, M. Richter and U. Ratsch (eds.), Perspectives on Adaptivity and Learning (2002), LNCS, Springer
    (2000 and 2001 runner-up)
  • Towards an Optimal Scoring Policy for Simulated Soccer Agents.
    Jelle R. Kok, Remco de Boer, Nikos Vlassis, and F.C.A. Groen.
    In G. Kaminka, P.U. Lima, and R. Rojas, editors, RoboCup 2002: Robot Soccer World Cup VI, pages 292-299, Fukuoka, Japan, 2002. Springer-Verlag.
    (2001 3rd place, 2002 4th place)
  • Advice Generation from Observed Execution: Abstract Markov Decision Process Learning.
    Patrick Riley and Manuela Veloso.
    In Proceedings of the Nineteenth National Conference on Artificial Intelligence (AAAI-2004), 2004.
    (2001 coach competition champion)
  • Global Planning from Local Perspective: An Implementation of Observation-based Plan Coordination in RoboCup Simulation Games.
    Cai Yunpeng, Chen Jiang, Yao Jinyi, and Li Shi.
    Pre-print available on-line, 2002.
    (2001, 2002 champion)
  • Team Formation for Reformation in Multiagent Domains like RoboCupRescue
    Ranjit Nair, Milind Tambe and Stacy Marsella.
    In Proceedings of RoboCup-2002 International Symposium, G. Kaminka, P. Lima and R. Roja (Eds.) Lecture Notes in Computer Science, Springer Verlag, 2003.
    (Rescue paper)
  • The high-level communication model for multiagent coordination in the RoboCupRescue Simulator"
    S.B.M. Post, M.L. Fassaert, A. Visser.
    in D. Polani, B. Browning, A. Bonarini, K. Yoshida (Eds.), RoboCup 2003, Lecture Notes on Artificial Intelligence, Vol. 3020, p. 503-509, 2004. Springer Verlag, Berlin.
  • Language Design for Rescue Agents.
    Itsuki Noda , Tomoichi Takahashi, Shuji Morita, Tetsuhiko Koto, Satoshi Tadokoro
    in Digital Cities II : Second Kyoto Workshop on Digital Cities, Kyoto, Japan, October 18-20, 2001
  • RoboCup-2008 Simulation league and the SSIL for qualification.
  • Rules of the 2007 RoboCup simulation league
  • Logfiles and team binaries from RoboCup 2007

  • Week 7: Swarms and self-organization

  • Slides from Thursday: (pdf).
  • Sven Koenig's Ant Robotics page, including a link to a java applet illustrating node counting.
  • Soccer server internet league
  • Team repository (up to 2002)
  • Demos of many agents steering to avoid one another based on simple local rules. (see in particular the ones under "combined behaviors and groups)
  • A paper on pair programming.
  • Blazing a trail: insect-inspired resource transportation by a robot team.
    Richard T. Vaughan, Kasper Stoy, Gaurav S. Sukhatme and Maja J Mataric.
    In Proceedings of the International Symposium on Distributed Autonomous Robot Systems, 2000.
  • AntNet: Distributed Stigmergetic Control for Communications Networks
    Di Caro, G. and Dorigo, M.
    Journal of Artificial Intelligence, Volume 9, pages 317-365 (1998).
  • When Ants Play Chess (Or Can Strategies Emerge From Tactical Behaviors?)
    Alexis Drogoul
    From Reaction to Cognition --- Fifth European Workshop on Modelling Autonomous Agents in a Multi-Agent World, MAAMAW-93 (LNAI Volume 957)
  • A workshop on Swarm robotics.

  • Week 8: Applications

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf). The ones on Intersection control (including the rest of Kurt's presentation on his life as a grad student).
  • Some applications papers read during previous years:
  • BDI-agents: from theory to practice.
    A. S. Rao and M. P. Georgeff.
    In Proceedings of the First International Conference on Multiagent Systems (ICMAS), 1995.
  • Improving Elevator Performance Using Reinforcement Learning. (cached copy in top right corner)
    R. Crites and A. Barto.
    In Advances in Neural Information Processing Systems 8 (NIPS8), D. S. Touretzky, M. C. Mozer, and M. E. Hasslemo (Eds.), Cambridge, MA: MIT Press, 1996, pp. 1017-1023.
  • Electric Elves : Applying Agent Technology to Support Human Organizations.
    Chalupsky, H., Gil, Y., Knoblock, C. A., Lerman, K., Oh, J., Pynadath, D., Russ, T. A., and Tambe, M.
    In proceedings of the International Conference of Innovative Application of Artificial Intelligence (IAAI'01), 2001.
  • ARCHON: A Distributed Artificial Intelligence System for Industrial Applications.
    D. Cockburn and N. R. Jennings.
    in Foundations of Distributed Artificial Intelligence (eds. G. M. P. O'Hare and N. R. Jennings)
    Wiley, 1996, 319-344.
  • Trafficopter: A Distributed Collection System for Traffic Information.
    Alexandros Moukas1 Konstantinos Chandrinos, and Pattie Maes.
    in (M. Klusch, G. Weiss eds.) Cooperative Information Agents II, Springer Verlag, 1998.
  • The traffic management project page with some follow-up papers and videos.
  • The simulator referred to in the paper.
  • A more recent paper on the topic, which handles human drivers and emergency vehicles.
  • 5th Workshop on Agents in Traffic and Transportation
  • An article in Wired about traffic intersections without any signs.

  • Week 9: Game Theory

  • Game theory slides from the course textbook.
  • Slides from Thursday: (pdf).
  • A study on Iterated Dominance and Nash Equilibrium
  • A brief survey on Multiagent Learning.
  • gametheory.net
  • Some useful slides (part C) from Michael Bowling on game theory, stochastic games, correlated equilibria; and (Part D) from Michael Littman with more on stochastic games.
  • A suite of game generators called GAMUT from Stanford.

  • Week 10: Game theory II + Statistical Measurement

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf).
  • Prisoner's dilemma contest
  • RoShamBo (rock-paper-scissors) contest
  • U. of Alberta page on automated poker.
  • On-line calculators of t-tests
  • Dr. Raymond Mooney's slides on statistical significance testing

  • Week 11: Distributed Rational Decision Making

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf).
  • Condorcet voting example
  • Types of tactical voting
  • Many voting methods defined

  • Week 12: Auctions

  • Slides from Tuesday: (pdf).
  • Slides from Thursday: (pdf).
  • Some writing tips. Some more (with more detail).
  • My class on Agent-Based E-Commerce from Fall 2006.
  • One of the introductory readings from that class:
    Auctions and Bidding: A Primer.
    Paul Milgrom.
    The Journal of Economic Perspectives, Vol. 3, No. 3. (Summer, 1989), pp. 3-22.
    Note: The above link works from UTCS machines, but may not work from an off-campus computer.
  • The Timing of Bids in Internet Auctions: Market Design, Bidder Behavior, and Artificial Agents.
    (get cached copy from upper right corner)
    Axel Ockenfels and Alvin E. Roth.
    AI Magazine, 23(3):79-88, Fall 2002.
  • A couple links about bidding rings on eBay:
  • A high-profile painting-based ring was busted.
  • Another later ring for glass.
  • Making More from Less: Strategic Demand Reduction in the FCC Spectrum Auctions.
    Robert J. Weber.
    The Journal of Economics and Management Strategy 6(3), 1997.
  • Self-enforcing Strategic Demand Reduction..
    Paul S. A. Reitsma, Peter Stone, Janos Csirik, and Michael L. Littman.
    In Agent Mediated Electronic Commerce IV: Designing Mechanisms and Systems, Lecture Notes in Artificial Intelligence, Springer Verlag, 2002.
  • Decision-Theoretic Bidding Based on Learned Density Models in Simultaneous, Interacting Auctions.
    Peter Stone, Robert E. Schapire, Michael L. Littman, Janos A. Csirik, and David McAllester.
    Journal of Artificial Intelligence Research, 19:209-242, 2003.
  • SICS Trading Agent Competition (TAC)

  • Week 13: Agent modeling

  • Slides from Tuesday: (pdf). Some more (on reinforcement learning - from Tom Mitchell's book Machine Learning)
  • Slides from Thursday:(pdf).
  • On behavior classification in adversarial environments.
    Patrick Riley and Manuela Veloso.
    In Proceedings of the Fifth International Symposium on Distributed Autonomous Robotic Systems (DARS-2000), 2000.
  • Implicit Negotiation in Repeated Games.
    Michael L. Littman and Peter Stone.
    In Proceedings of The Eighth International Workshop on Agent Theories, Architectures, and Languages (ATAL-2001), pp. 393-404, August 2001.
  • The General Game Playing competition.

  • Week 14: Multiagent Learning

  • Slides from Thursday: (pdf). Some more on transfer learning: (ppt).
  • Methods for Competitive Co-evolution: Finding Opponents Worth Beating.
    Christopher D. Rosin and Richard K. Belew.
    Proceedings of the Sixth International Conference on Genetic Algorithms, 1995.
  • Layered Learning.
    Peter Stone and Manuela Veloso.
    Eleventh European Conference on Machine Learning, 2000.
  • Concurrent Layered Learning.
    Shimon Whiteson and Peter Stone.
    In Second International Joint Conference on Autonomous Agents and Multiagent Systems, July 2003.
  • Layered Learning on Physical Robots
  • keepaway site
  • half field offense

  • Week 15: Entertainment Agents

  • Slides from Tuesday: (pdf). Some more on entertainment agents in general (ppt) (by Vinay Sampath Kumar). (ps.gz) (by Charles Isbell).
  • Slides from Thursday: (pdf). The ones from Elaine Rich on natural language agents: (ppt). The cobot ones
  • An Architecture for Action, Emotion, and Social Behavior.
    Joseph Bates, A. Bryan Loyall, and W. Scott Reilly.
    in Artificial Social Systems: Fourth European Workshop on Modeling Autonomous Agents in a Multi-Agent World, Springer-Verlag, Berlin, 1994.
    This is a paper on the Oz project
  • Creatures: Artificial Life Autonomous Software Agents for Home Entertainment.
    Stephen Grand, Dave Cliff, and Anil Malhotra.
    Millenium technical report 9601, 1996.
  • Alice recently played the Turing Original Imitation Game. See also a Slashdot article on it.

  • The tournament!

  • The slides presented during the tourney, including results: (pdf).

  • [Back to Department Homepage]

    Page maintained by Peter Stone
    Questions? Send me mail