Abstract
Adaptive learning techniques can automate the large-scale coordination of multi-agent systems and enhance their robustness in dynamic environments. Several learning approaches have been developed to address the different aspects of coordination, from learning coordination rules to the integrated learning of trust and reputation in order to facilitate coordination in open systems. Although convergence in multi-agent learning is still an open research question, several applications have emerged using some of the learning techniques presented.
Keywords
Differential Evolution Multiagent System Markov Decision Process Team Learning Coordination Rule
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Toshiharu Sugawara and Victor Lesser, “Learning Coordination Plans in Distributed Problem-solving Environments”, In Twelfth International Workshop on Distributed Artificial Intelligence, 1993.Google Scholar
- 2.Tom Mitchell, “The Discipline of Machine Learning”, Technical Report CMU-ML-06–108, Carnegie Mellon University, 2006.Google Scholar
- 3.Anita Raja and Victor Lesser, “Reasoning about Coordination Costs in Resource-bounded Multi-agent Systems”, In Proceedings of the American Association for Artificial Intelligence (AAAI), 2004.Google Scholar
- 4.Lynn Parker, “L-ALLIANCE: Task-oriented Multi-robot Learning in Behaviour-based Systems”, In Advanced Robotics, Special Issue on Selected Papers from IROS'96, pp. 305–322, 1997.Google Scholar
- 5.Thomas H. Labella, Marco Dorigo, and Jean- Louis Deneubourg, “Efficiency and Task Allocation in Prey Retrieval”, In Proceedings of the First International Workshop on Biologically Inspired Approaches to Advanced Information Technology (Bio-ADIT2004), Lecture Notes in Computer Science, Springer Verlag, pp. 32–47, 2004.Google Scholar
- 6.Myriam Abramson, William Chao, and Ranjeev Mittu, “Design and Evaluation of Distributed Role Allocation Algorithms in Open Environments”, In International Conference on Artificial Intelligence, 2005.Google Scholar
- 7.Yoav Shoham, Rob Powers, and Trond Grenager, “If Multi-agent Learning is the Answer, What is the Question?”, In Artificial Intelligence Journal, Vol. 171, No. 7, pp. 365–377, 2007.MATHCrossRefMathSciNetGoogle Scholar
- 8.Peter Stone, “Multiagent Learning is not the Answer. It is the Question”, In Artificial Intelligence Journal, Vol. 171, No. 7, pp. 402–405, 2007.MATHCrossRefGoogle Scholar
- 9.Sandip Sen and Mahendra Sekaran, “Multiagent Coordination with Learning Classifier Systems”, In Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems at AAMAS, Springer Verlag, pp. 218–233, 2005.Google Scholar
- 10.Marco Dorigo and Hugues Bersini, “A Comparison of Q-learning and Classifier Systems, In Proceedings of From Animals to Animats”, In Third International Conference on Simulation of Adaptive Behavior, MIT Press, pp. 248–255, 1994.Google Scholar
- 11.Gerhard Weiss, “Learning to Coordinate Actions in Multi-agent Systems”, In Readings in Agents, Morgan Kaufmann Publishers Inc. pp. 481–486, 1997.Google Scholar
- 12.Pragnesh J. Modi, “An Asynchronous Complete Method for Distributed Constraint Satisfaction”, In Autonomous Agents and Multiagent Systems (AAMAS), pp. 161–168, 2001.Google Scholar
- 13.Claus Boutilier, “Learning Conventions in Multiagent Stochastic Domains using Likelihood Estimates”, In Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence, pp. 106–114, 1996.Google Scholar
- 14.Mitchell A. Potter, and Kenneth A. D Jong, “Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents”, In Evolutionary Computation, Vol. 8, pp. 1–29, 2000.Google Scholar
- 15.Eric Bonabeau, Marco Dorigo, and Guy Theraulaz, “Swarm Intelligence: From Natural to Artificial Systems”, Oxford University Press, USA, 1999.MATHGoogle Scholar
- 16.Thomas Haynes, Kit Lau, and Sandip Sen, “Learning Cases to Compliment Rules for Conflict Resolution in Multiagent Systems”, In Working Notes for the AAAI Symposium on Adaptation, Co-evolution and Learning in Multiagent Systems, AAAI Press, pp. 51–56, 1996.Google Scholar
- 17.M. Benda, V. Jagannathan, and R. Dodhiawalla, “On Optimal Cooperation of Knowledge Sources”, Technical Report BCS-G2010–28, Boeing AI Center, Boeing Computer Services, 1985.Google Scholar
- 18.Hiroaki Kitano, Milind Tambe, Peter Stone, Manuela Veloso, Silvia Coradeschi, Eiichi Osawa, Hitoshi Matsubara, Itsuki Noda, and Minoru Asada, “The RoboCup Synthetic Agent Challenge 97”, In Fifteenth International Join Conference on Artificial Intelligence, San Francisco, CA, Morgan Kaufmann, pp. 24–29, 1997.Google Scholar
- 19., Peter Stone, and Manuela Veloso, “Layered Learning”, In Proceedings of the Eleventh European Conference on Machine Learning, Springer Verlag, pp. 369–381, 2000.Google Scholar
- 20.Tom G. Dietterich, “The MAXQ Method for Hierarchical Reinforcement Learning”, In Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann, pp. 118–126, 1998.Google Scholar
- 21.Martin L. Putterman, “Markov Decision Processes”, 2nd edn., Wiley-Interscience, 2005.Google Scholar
- 22.Robert Axelrod, “The Evolution of Cooperation”, Basic Books, 1984.Google Scholar
- 23.Andreas Birk, “Boosting Cooperation by Evolving Trust”, Applied Artificial Intelligence, Vol. 14, pp. 769–784, 2000.Google Scholar
- 24.Milind Tambe, Paul Scerri, and David V. Pynadath, “Adjustable Autonomy for the Real World”, In Proceedings of AAAI Spring Symposium on Safe Learning Agents, pp. 43–53, 2002.Google Scholar
- 25.Paul Scerri, David V. Pynadath, Nathan Schurr, Alessandro Farinelli, Sudeep Gandhe, and Milind Tambe, “Team Oriented Programming and Proxy Agents: The Next Generation”, In Workshop on Programming MultiAgent Systems at AAMAS, 2004.Google Scholar
- 26.Ronald Parr, and Stuart Russell, “Reinforcement learning with Hierarchies of Machines”, In Neural Information Processing Systems, 1998.Google Scholar
- 27.Myriam Abramson, “Training Coordination Proxy Agents using Reinforcement Learning”, Technical report, Fall Symposium of the American Association of Artificial Intelligence (AAAI), 2006.Google Scholar
- 28.Gianni D. Caro and Marco Dorigo, “AntNet: Distributed Stigmergetic Control for Communications Networks”, In Journal of Artificial Intelligence Research, No. 9, pp. 317–365, 1998.Google Scholar
- 29.Avi Rosenfeld, Gal Kaminka, and Sarit Kraus, “Adaptive Robot Coordination Using Interference Metrics”, In Proceedings of The Sixteenth European Conference on Artificial Intelligence, 2004.Google Scholar
- 30.Jumpol Polvichai, Paul Scerri, and Michael Lewis, “An Approach to Online Optimization of Heuristic Coordination Algorithms”, In Proceedings of the 7th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS), 2008.Google Scholar
- 31.Myriam Abramson, Ranjeev Mittu, and Jean Berger, “Coordination Challenges and Issues in Stability, Security, Transition and Reconstruction (SSTR) and Cooperative Unmanned Aerial Vehicles”, In International Conference on Integration of Knowledge Intensive Multi-Agent Systems (KIMAS), pp. 428–433, 2007.Google Scholar
- 32.Ionnis K. Nikolos, and A.N. Brintaki, “Coordinated UAV Path Planning using Differential Evolution”, In Proceedings of the 13th Mediterranean Conference on Control and Automation, 2005.Google Scholar
- 33.Rainier Storn, and Kenneth Price, “Differential Evolution: a Simple and Efficient Adaptive Scheme for Global Optimization over Continuous Spaces”, Technical Report TR-95–012, Berkeley, 1995.Google Scholar
- 34.H. Van Dyke Parunak, Sven Brueckner, and John Sauter, “Digital Pheromones Mechanisms for Coordination of Unmanned Vehicles”, In Proceedings of the 1st Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS), 2002.Google Scholar
Copyright information
© Springer-Verlag US 2009