How to Design an Autonomous Creature Based on Original Artificial Life Approaches

Abstract

We introduce new approaches for creating of autonomous agents. The life of such creatures is very similar to the animal’s life in the Nature, which learns autonomously from the simple tasks towards the more complex ones and is inspired by AI, Biology and Ethology. We present our established design of artificial creature, capable of learning from its experience in order to fulfill more complex tasks, which is based mainly on ethology. It integrates several types of action-selection mechanisms and learning into one system. The main advantages of the architecture is its autonomy, the ability to gain all information from the environment and decomposition of the decision space into the hierarchy of abstract actions, which dramatically reduces the total size of decision space. The agent learns how to exploit the environment continuously, where the learning of new abilities is driven by his physiology, autonomously created intentions, planner and neural network.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Horáková, J., Kelemen, J.: From Rossums Universal Robots Toward Post-Human. In: Cybernetics and Systems, vol. 2, pp. 774–779. Austrian Society for Cybernetic Studies, Austria (2004)Google Scholar
  2. 2.
    Kelemen, J.: Myslenie a stroj, nakladatelstvo Kalligram, Bratislava, p. 384 (2010)Google Scholar
  3. 3.
    Husbands, P., Holland, O., Wheeler, M. (eds.): The Mechanical Mind in History. MIT Press (2008)Google Scholar
  4. 4.
    Steels, L., Brooks, R.: The artificial life route to artificial intelligence: Building Situated Embodied Agents. Lawrence Erlbaum Ass., New Haven (1994)Google Scholar
  5. 5.
    Wooldridge, M.R.: An Introduction to Multi-Agent Systems. John Wiley & Sons, New York (2002)Google Scholar
  6. 6.
    Albus, J.S.: A New Approach to Manipulator Control: the Cerebellar Model Articulation Controller (CMAC). Trans. ASME, Series G. Journal of Dynamic Systems, Measurement and Control 97, 220–233 (1975)MATHCrossRefGoogle Scholar
  7. 7.
    Handelman, D.A., Lane, S.H., Gelfand, J.J.: Integrating neural networks and knowledge-based systems for intelligent robotic control. IEEE Control Systems Magazine 10, 77–87 (1990)CrossRefGoogle Scholar
  8. 8.
    Ryan, M., Pendrith, M.: RL-TOPs: An Architecture for Modularity and Re-Use in Reinforcement Learning. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 481–487 (1998)Google Scholar
  9. 9.
    Nilsson, N.J.: Teleo-reactive programs for agent control. Journal of Artificial Intelligence Research 1, 139–158 (1994)Google Scholar
  10. 10.
    Vítků, J.: An Artificial Creature Capable of Learning from Experience in Order to Fulfill More Complex Tasks, CTU in Prague, FEE, Diploma thesis supervised by Nahodil, P., p. 142 (2011)Google Scholar
  11. 11.
    Kadleček, D.: Motivation Driven Reinforcement Learning and Automatic Creation of Behavior Hierarchies, CTU in Prague, FEE, PhD thesis supervised by Nahodil, P., p.143 (2008)Google Scholar
  12. 12.
    Kadleček, D., Nahodil, P.: New Hybrid Architecture in Artificial Life Simulation. In: Kelemen, J., Sosík, P. (eds.) ECAL 2001. LNCS (LNAI), vol. 2159, pp. 143–146. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  13. 13.
    Nahodil, P., Kadleček, D.: Adopting Animal Concepts in Hierarchical Reinforcement Learning and Control of Intelligent Agents. In: Proc. of 2nd IEEE/RAS-EMBS Intern. Conf. on Biomedical Robotics and Biomechatronics, BioRob, Scottsdale, pp. 122–131 (2008)Google Scholar
  14. 14.
    Grand, S.: Creation: Life and How to Make It, p. 230. Harvard University Press (2003)Google Scholar
  15. 15.
    Fikes, R., Nilsson, N.: STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving. Artificial Intelligence 2, 189–208 (1971)MATHCrossRefGoogle Scholar
  16. 16.
    Sacerdoti, E.D.: Planning in a Hierarchy of Abstraction Spaces. Artificial Intelligence 5(2), 115–135 (1974)MATHCrossRefGoogle Scholar
  17. 17.
    Erol, K., Nau, D., Hendler, J.: HTN Planning: Complexity and Expressivity. In: Proc. National Conference on Artificial Intelligence (AAAI 1994), pp. 1123–1128. MIT Press, Seattle (1994)Google Scholar
  18. 18.
    Sardina, S., de Silva, L., Padgham, L.: Hierarchical Planning in BDI Agent Programming Languages: a Formal Approach. In: AAMAS 2006 Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 1001–1008. ACM Press, NY (2006)CrossRefGoogle Scholar
  19. 19.
    Ryan, M., Pendrith, M.: RL-TOPs: An Architecture for Modularity and Re-Use in Reinforcement Learning. In: Proc. of the 15th International Conference on Machine Learning, pp. 481–487 (1998)Google Scholar
  20. 20.
    Ross, M.: Hierarchical Reinforcement Learning: A Hybrid Approach, PhD Thesis, The UNI of New South Wales, School of Computer Science and Engineering (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Department of CyberneticsCTU in Prague, FEEPrague 6Czech Republic

Personalised recommendations