Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지

Multiple Behavior s Learning and Prediction in Unknown Environment

  • Song, Wei (Dept. of Multimedia, Graduate School of Digital Image & Contents, Dongguk University) ;
  • Cho, Kyung-Eun (Dept. of Game & Multimedia, Dongguk University) ;
  • Um, Ky-Hyun (Dept. of Game & Multimedia, Dongguk University)
  • Received : 2010.11.29
  • Accepted : 2010.12.28
  • Published : 2010.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

When interacting with unknown environments, an autonomous agent needs to decide which action or action order can result in a good state and determine the transition probability based on the current state and the action taken. The traditional multiple sequential learning model requires predefined probability of the states' transition. This paper proposes a multiple sequential learning and prediction system with definition of autonomous states to enhance the automatic performance of existing AI algorithms. In sequence learning process, the sensed states are classified into several group by a set of proposed motivation filters to reduce the learning computation. In prediction process, the learning agent makes a decision based on the estimation of each state's cost to get a high payoff from the given environment. The proposed learning and prediction algorithms heightens the automatic planning of the autonomous agent for interacting with the dynamic unknown environment. This model was tested in a virtual library.

Keywords

References

  1. F. Stan and G. Art, "Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents," Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, pp.21-35, 1996.
  2. I. Szita, M. Ponsen, and P. Spronck, "Effective and Diverse Adaptive Game AI," IEEE Transactions on Computational Intelligence and AI in Games, March 2009, pp.16-27, 2009.
  3. N.F. Xiao and S. Nahavandi, "A reinforcement learning approach for robot control in an unknown environment," IEEE International Conference on Industrial Technology, Vol.2, pp.1096-1099, 2002.
  4. S. Proper and P. Tadepalli, "Solving multiagent assignment Markov decision processes," Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems, pp.681-689, 2009.
  5. W. Song, K. Cho, and K. Um, "Motivated based Multiple Behaviors Learning in Unknown Environment," J. of Korea Multimedia Society, Vol.12, No.12, pp.1819-1824, 2009.
  6. L.P. Kaelbling, L.M. Littman, and A.W. Moore, "Reinforcement learning: a survey," J. of Artificial Intelligence Research, Vol. 4, No.11, pp.237-285, 1996.
  7. T.M. Gureckis and B.C. Love, "Short-term gains, long-term pains: How cues about state aid learning in dynamic environments," J. of Cognition, Vol.113, No.3, pp.293-313, 2009. https://doi.org/10.1016/j.cognition.2009.03.013
  8. R. Sun and C. Sessions, "Learning plans without a priori knowledge," J. of Adaptive Behavior, Vol.8, No.3/4, pp.225-253, 2000. https://doi.org/10.1177/105971230000800302
  9. M. Kwiatkowska, G. Norman, and D. Parker, "Game-based Abstraction for Markov Decision Processes," Proceedings of the 3rd international conference on the Quantitative Evaluation of Systems, pp.157-166, 2006.
  10. S. Siddiqi and A. Moore, "Fast Inference and Learning in Large-State-Space HMMs," Proceedings of the 22nd International Conference on Machine Learning, Vol. 119, pp.800-807, 2005.
  11. S. Timmer and M. Riedmiller, "Learning Policies for Abstract State Spaces," 2005 IEEE International Conference on Systems, Man and Cybernetics, Vol. 4, pp.3179-3184, 2005.
  12. L.H. Li, V. Bulitko, and R. Greiner, "Focus of attention in reinforcement learning," J. of Universal Computer Science, Vol. 13, No. 9, pp.1246-1269, 2007.
  13. Z.C. Qin and J. Lawry, "Decision tree learning with fuzzy labels," Information Sciences, Vol. 172, pp.91-129, 2005. https://doi.org/10.1016/j.ins.2004.12.005
  14. E.D. Sevin and D. Thalmann, "A Motivational Model of Action Selection for Virtual Humans," Computer Graphics International (CGI), IEEE Computer Society Press, pp.213-220, 2005.
  15. S. Singh, A.G. Barto, and N. Chentanez, "Intrinsically Motivated Reinforcement Learning," Proceedings of Advances in Neural Information Processing Systems 17 (NIPS), 2005.
  16. K. Merrick, "Modelling Motivation for Experience-Based Attention Focus in Reinforcement Learning," PhD Thesis, University of Sydney, 2007.
  17. R.S. Sutton and A.G. Barto, "Reinforcement Learning: An Introduction," MIT Press, A Bradford Book, Cambridge, MA, 1998.