Advertisement

Lazy Fully Probabilistic Design: Application Potential

  • Tatiana V. Guy
  • Siavash Fakhimi Derakhshan
  • Jakub Štěch
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10767)

Abstract

The article addresses a lazy learning approach to fully probabilistic decision making when a decision maker (human or artificial) uses incomplete knowledge of environment and faces high computational limitations. The resulting lazy Fully Probabilistic Design (FPD) selects a decision strategy that moves a probabilistic description of the closed decision loop to a pre-specified ideal description. The lazy FPD uses currently observed data to find past closed-loop similar to the actual ideal model. The optimal decision rule of the closest model is then used in the current step. The effectiveness and capability of the proposed approach are manifested through example.

Keywords

Lazy learning Fully Probabilistic Design Decision making Linear quadratic gaussian control 

Notes

Acknowledgement

The authors would like to thank Miroslav Kárný for valuable discussions and comments. The research has been partially supported by the Czech Science Foundation, project GA16-09848S.

References

  1. 1.
    Kárný, M., et al. (eds.): Optimized Bayesian Dynamic Advising: Theory and algorithms. Springer, London (2006).  https://doi.org/10.1007/1-84628-254-3
  2. 2.
    Kárný, M.: Towards fully probabilistic control design. Automatica 32(12), 1719–1722 (1996)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Savage, L.J.: The Foundations of Statistics, pp. 188–190. Wiley, NY (1954)zbMATHGoogle Scholar
  4. 4.
    Bellman, R.: Adaptive Control Processes. Princeton Press, NJ (1961)CrossRefGoogle Scholar
  5. 5.
    Roll, J., Nazin, A., Ljung, L.: Nonlinear system identification via direct weight optimization. Automatica 41(3), 475–490 (2005)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Powell, W.B.: Approximate Dynamic Programming: Solving the Curses of Dimensionality. vol. 703. Wiley (2007)Google Scholar
  7. 7.
    Aha, D.W.: Artif. Intell. Rev. Special Issue Lazy Learn. 11, 1–5 (1997)Google Scholar
  8. 8.
    Aamodt, A., Plaza, E.: Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun. 7(1), 39–59 (1994)Google Scholar
  9. 9.
    Bitanti, S., Picci, G.: Identification, adaptation, learning. NATO ASI Series F on Computer and Systems Sciences (1996)Google Scholar
  10. 10.
    Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. Journal of Big Data 3(1), 9 (2016)CrossRefGoogle Scholar
  11. 11.
    Klenk, M., Aha, D.W., Molineaux, M.: The case for case-based transfer learning. AI Mag. 32(1), 54 (2011)CrossRefGoogle Scholar
  12. 12.
    Kullback, S., Leibler, R.A.: On information and sufficiency. The Ann. Math. Stat. 22(1), 79–86 (1951)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Peterka, V.: Bayesian approach to system identification. Trends Progress Syst. Ident. 1, 239–304 (1981)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Kulhavy, R., Kárný, M.: Tracking of slowly varying parameters by directional forgetting. In: Proceedings of the 9th IFAC World Congress, vol. 10, pp. 78–83 (1984)CrossRefGoogle Scholar
  15. 15.
    Adachi, S., Hashimoto, S., Miyamori, G., Tan, A.: Autonomous flight control for a large-scale unmanned helicopter. IEEJ Trans. Ind. Appl. 121(12), 1278–1283 (2001)CrossRefGoogle Scholar
  16. 16.
    Gil, I.A., Barrientos, A., Del Cerro, J.: Attitude control of a minihelicopter in hover using different types of control. Revista Técnica de la Facultad de Ingeniería. Universidad del Zulia 29(3) (2006)Google Scholar
  17. 17.
    Ambrosino, G., Celentano, G., Garofalo, F.: Decentralized PD controllers for tracking control of uncertain multivariable systems. IFAC Proc. Vol. 18(5), 1907–1911 (1985)CrossRefGoogle Scholar
  18. 18.
    Hou, Z.S., Wang, Z.: From model-based control to data-driven control: Survey, classification and perspective. Inf. Sci. 235(Suppl. C), 3–35 (2013)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Kárný, M., Guy, T.V.: Preference elicitation in fully probabilistic design of decision strategies. In: Proceedings of the 49th IEEE Conference on Decision and Control (2010)Google Scholar
  20. 20.
    Braziunas, D., Boutilier, C.: Preference elicitation and generalized additive utility (nectar paper). In: Proceedings of the 21st National Conference on AI (AAAI-2006), Boston, MA (2006)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Tatiana V. Guy
    • 1
  • Siavash Fakhimi Derakhshan
    • 1
  • Jakub Štěch
    • 1
  1. 1.Department of Adaptive SystemsInstitute of Information Theory and Automation, The Czech Academy of SciencesPrague 8Czech Republic

Personalised recommendations