FUZZY REINFORCEMENT LEARNING FOR EMBEDDED SOCCER AGENTS IN A MULTI-AGENT CONTEXT

A.M. Tehrani, M.S. Kamel, and A.M. Khamis

References

  1. [1] H. Kitano, M. Asada, Y. Kuniyoshi, I. Noda, E. Osawa, &H. Matsubara, Robocup: A challenge problem for AI androbotics, in H. Kitano (Ed.), RoboCup-97: Robot Soccer WorldCup V LNAI 1395 (Nagoya, Japan: Springer-Verlag, 1998),1–19.
  2. [2] M. Wooldrige & N. Jennings, Intelligent agents: Theory andpractice, The Knowledge Engineering Review, 10 (2), 1995,115–152.
  3. [3] M. Wooldridge & P. Ciancarini, Agent-oriented software engi-neering: The state of the art, in P. Ciancarini & M. Wooldridge(Eds.), 1st Int. Workshop on Agent-oriented Software Engi-neering, AOSE 2000, Lecture notes in AI volume 1957 (Ale-mania, Berlin: Springer-Verlag, 2001), 1–28. doi:10.1007/3-540-44564-1_1
  4. [4] S. Russell & P. Norvig, Artificial intelligence: A modernapproach (Englewood Cliffs, NJ: Prentice-Hall, 1995).
  5. [5] P. Stone & M. Veloso, Towards collaborative and adversariallearning: A case study in robotic soccer, Int. Journal of HumanComputer Studies, 48 (1), 1998, 83–104. doi:10.1006/ijhc.1997.0162
  6. [6] J. Brusey, Learning behaviours for robot soccer, doctoral diss.,RMIT University, Australia, 2002.
  7. [7] E. Uchibe, M. Asada, & K. Hosoda, Behaviour coordinationfor a mobile robot using modular reinforcement learning, Proc.IEEE/RSJ Int. Conf. on Intelligent Robots and Systems 1996(IROS ’96), Osaka, Japan, 1996, 1329–1336. doi:10.1109/IROS.1996.568989
  8. [8] P. Stone & M. Veloso, Team-partitioned, opaque-transitionreinforcement learning, in M. Asada & H. Kitano (Eds.),RoboCup-98: Robot Soccer World Cup II (Berlin: Springer-Verlag, 1999).
  9. [9] T. Balch, Learning roles: Behavioural diversity in robot teams,Technical report GIT-CC-97-12, College of Computing, GeorgiaInstitute of Technology, Atlanta, Georgia, 1997.
  10. [10] P. Stone, R.S. Sutton, & S. Singh, Reinforcement learning for3 vs. 2 keepaway, in P. Stone, T. Balch, & G. Kraetzschmar(Eds.), RoboCup-2000: Robot Soccer World Cup IV: LectureNotes in Artificial Intelligence 2019 (Melbourne, Australia:Springer-Verlag, 2001), 249–258. doi:10.1007/3-540-45324-5_23
  11. [11] P. Stone & R. Sutton, Scaling reinforcement learning towardRoboCup soccer, Proc. 18th Int. Conf. on Machine Learning,San Francisco, CA, 2001, 537–544.
  12. [12] A. Tehrani & M. Kamel, A reinforcement learning approachto behaviour arbitration, Proc. 2nd FIRA Robot Soccer WorldCongress, Vienna, Austria, 2003, 233–238.
  13. [13] T. Graepel, R. Herbrich, & J. Gold, Learning to fight, Proc.Int. Conf. on Computer Games: Artificial Intelligence, Designand Education, Microsoft Campus, Reading, UK, 2004.
  14. [14] C. Zhou, Robot learning with GA-based fuzzy reinforcementlearning agents, Information Sciences, 145, 2002, 45–68. doi:10.1016/S0020-0255(02)00223-2
  15. [15] C. Zhou & Q. Meng, Dynamic balance of a biped robot usingfuzzy reinforcement learning agents, Fuzzy Sets and Systems,134 (1), 2003, 169–187. doi:10.1016/S0165-0114(02)00236-1
  16. [16] A. Tehrani & M. Kamel, Fuzzy reinforcement learning forembedded soccer agents in a multiagent context, Proc. of theAgents Meet Robots Workshop, in conjunction with the 17thCanadian Conf. on Artificial Intelligence AI 2004, London,Ontario, 2004, 69–74.
  17. [17] T. Finin, R. Fritzson, D. McKay, & R. McEntire, KQMLas an agent communication language, Proc. 3rd Int. Conf.118on Information and Knowledge Management (CIKM ’94),Gaithersburg, MD, 1994, 456–463. doi:10.1145/191246.191322
  18. [18] G. Rummery & M. Niranjan, On-line Q-learning using con-nectionist systems, Technical report CUED/F-INFENG/TR166, Cambridge University, Cambridge, UK, 1994.
  19. [19] R. Sutton & A. Barto, Reinforcement learning: An introduction(Cambridge, MA: MIT Press, 1998).
  20. [20] A. Tehrani & M. Kamel, An agent oriented simulation systemfor soccer playing robots, Proc. 2nd FIRA Robot Soccer WorldCongress, Vienna, Austria, 2003, 273–278.
  21. [21] A. Tehrani & M. Kamel, A methodology for specifying anddesigning behaviours for mobile robots, Proc. World Automa-tion Congress (WAC2004) in Soft Computing and IndustrialApplications, Seville, Spain, 2004, 55–61.

Important Links:

Go Back