Advertisement

Motivated Reinforcement Learning Using Self-Developed Knowledge in Autonomous Cognitive Agent

  • Piotr Papiez
  • Adrian HorzykEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10841)

Abstract

This paper describes the development of a cognitive agent using motivated reinforcement learning. The conducted research was based on the example of a virtual robot, that placed in an unknown maze, was learned to reach a given goal optimally. The robot should expand knowledge about the surroundings and learn how to move in it to achieve a given target. The built-in motivation factors allow it to focus initially on collecting experiences instead of reaching the goal. In this way, the robot gradually broadens its knowledge with the advancement of exploration of its surroundings. The correctly formed knowledge is used for effective controlling the reinforcement learning routine to reach the target by the robot. In such a way, the motivation factors allow the robot to adapt and control its motivated reinforcement learning routine automatically and autonomously.

Keywords

Neural networks Environment adapted reinforcement learning Knowledge-based learning and supervision Motivated learning Knowledge development Cognitive systems Cognitive robot 

Notes

Acknowledgments

This work was supported by AGH 11.11.120.612 and the grant from the National Science Centre DEC-2016/21/B/ST7/02220.

References

  1. 1.
    Duch, W.: Brain-inspired conscious computing architecture. J. Mind Behav. 26, 1–22 (2005)Google Scholar
  2. 2.
    Horzyk, A., Starzyk, J.A., Graham, J.: Integration of semantic and episodic memories. IEEE Trans. Neural Netw. Learn. Syst. 28(12), 3084–3095 (2017)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Horzyk, A.: How does generalization and creativity come into being in neural associative systems and how does it form human-like knowledge? Neurocomputing 144, 238–257 (2014)CrossRefGoogle Scholar
  4. 4.
    Horzyk, A.: Artificial Associative Systems and Associative Artificial Intelligence, pp. 1–276. EXIT, Warsaw (2013)Google Scholar
  5. 5.
    Horzyk, A.: Human-like knowledge engineering, generalization, and creativity in artificial neural associative systems. In: Skulimowski, A.M.J., Kacprzyk, J. (eds.) Knowledge, Information and Creativity Support Systems: Recent Trends, Advances and Solutions. AISC, vol. 364, pp. 39–51. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-19090-7_4CrossRefGoogle Scholar
  6. 6.
    Kalat, J.W.: Biological Grounds of Psychology. PWN, Warsaw (2006)Google Scholar
  7. 7.
    Larose, D.T.: Discovering Knowledge from Data: Introduction to Data Mining. PWN, Warsaw (2006)zbMATHGoogle Scholar
  8. 8.
    Rutkowski, L.: Techniques and Methods of Artificial Intelligence. PWN, Warsaw (2012)Google Scholar
  9. 9.
    Tadeusiewicz, R.Y.: New trends in neurocybernetics. Comput. Methods Mater. Sci. 10(1), 1–7 (2010)Google Scholar
  10. 10.
    Smart, W.D.: Making reinforcement learning work on real robots. Ph.D. dissertation, Department of Computer Science, Brown University, Providence, RI (2002)Google Scholar
  11. 11.
    Papiez, P.: Use of a neural network to move a robot to the designated target position in a maze using reinforcement learning. Engineering dissertation, AGH University of Science and Technology in Krakow, Supervised and Promoted by A. Horzyk (2018)Google Scholar
  12. 12.
    Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning: a survey. Int. J. Robot. Res. 32, 1238–1274 (2013)CrossRefGoogle Scholar
  13. 13.
    Starzyk, J.A.: Motivated learning for computational intelligence. In: Igelnik, B. (ed.) Computational Modeling and Simulation of Intellect: Current State and Future Perspectives (Chap. 11), pp. 265–292. IGI Publishing, Hershey (2011)CrossRefGoogle Scholar
  14. 14.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  15. 15.
    Janowski, M.: Use of a neural network to move a robot back to the starting position in a maze using supervised learning. Engineering dissertation, AGH University of Science and Technology in Krakow, Supervised and Promoted by A. Horzyk (2018)Google Scholar
  16. 16.
    Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with Deep Reinforcement Learning. arXiv preprint arXiv:1312.5602 (2013)
  17. 17.
    Starzyk, J.A., Graham, J., Horzyk, A.: Trust in motivated learning agents. In: 2016 IEEE SSCI, pp. 1–8. Inc. 57 Morehouse Lane Red Hook, NY, 12571, USA. IEEE Xplore (2016).  https://doi.org/10.1109/SSCI.2016.7850027, ISBN 978-1-5090-4239-5
  18. 18.
    Tadeusiewicz, R.: Introduction to intelligent systems. In: Wilamowski, B.M., Irvin, J.D. (eds.) The Industrial Electronics Handbook Intelligent Systems, pp. 1–12. CRC Press, Boca Raton (2011)Google Scholar
  19. 19.
    Matiisen, T.: Demystifying Deep Reinforcement Learning (2015). http://neuro.cs.ut.ee/demystifying-deep-reinforcement-learning
  20. 20.
    Tadeusiewicz, R., Horzyk, A.: Man-machine interaction improvement by means of automatic human personality identification. In: Saeed, K., Snášel, V. (eds.) CISIM 2014. LNCS, vol. 8838, pp. 278–289. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-662-45237-0_27CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.AGH University of Science and TechnologyKrakowPoland

Personalised recommendations