Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Real Time Robot Policy Adaptation Based on Intelligent Algorithms

  • Conference paper

Abstract

In this paper we present a new method for robot real time policy adaptation by combining learning and evolution. The robot adapts the policy as the environment conditions change. In our method, we apply evolutionary computation to find the optimal relation between reinforcement learning parameters and robot performance. The proposed algorithm is evaluated in the simulated environment of the Cyber Rodent (CR) robot, where the robot has to increase its energy level by capturing the active battery packs. The CR robot lives in two environments with different settings that replace each other four times. Results show that evolution can generate an optimal relation between the robot performance and exploration-exploitation of reinforcement learning, enabling the robot to adapt online its strategy as the environment conditions change.

Similar content being viewed by others

Keywords

References

  1. Sutton, R.S., Barto, A.G.: Reinforcement learning. MIT Press, Cambridge (1998)

    Google Scholar 

  2. Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4, 237–285 (1996)

    Google Scholar 

  3. Minato, T., Asada, M.: Environmental change adaptation for mobile robot navigation. Journal of Robotics Society of Japan 18(5), 706–712 (2000)

    Google Scholar 

  4. Matsui, T., Inuzuka, N., Seki, H.: Adapting to subsequent changes of environment by learning policy preconditions. Int. Journal of Computer and Information Science 3(1), 49–58 (2002)

    Google Scholar 

  5. Doya, K.: Reinforcement learning in continuous time and space. Neural Computation 12, 219–245 (2000)

    Article  Google Scholar 

  6. Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving networks: using the genetic algorithm with connectionist learning. In: Langton, C.G., et al. (eds.) Artificial Life II, pp. 511–547. Addison Wesley, Reading (1990)

    Google Scholar 

  7. Unemi, T.: Evolutionary differentiation of learning abilities - a case study on optimizing parameter values in Q-learning by a genetic algorithm. In: Brooks, R.A., Maes, P. (eds.) Artificial Life IV - Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems, pp. 331–336. MIT Press, Cambridge (1994)

    Google Scholar 

  8. French, R.M., Messinger, A.: Genes, phenes and the baldwin effect: learning and evolution in a simulated population. In: Proc. of Forth Int. Workshop on the Synthesis and Simulation of Living Systems, pp. 277–282 (1977)

    Google Scholar 

  9. Nolfi, S., Parisi, D.: Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior 5(1), 75–98 (1996)

    Article  Google Scholar 

  10. Niv, Y., Joel, D., Meilijson, I., Ruppin, E.: Evolution of reinforcement learning in uncertain environments: A simple explanation for complex foraging behaviors. Adaptive Behavior 10(1), 5–24 (2002)

    Article  Google Scholar 

  11. Capi, G., Doya, K.: Application of evolutionary computation for efficient reinforcement learning. Applied Artificial Intelligence 20(1), 1–20 (2005)

    Google Scholar 

  12. Eriksson, A., Capi, G., Doya, K.: Evolution of metaparameters in reinforcement learning. In: IROS 2003 (2003)

    Google Scholar 

  13. Capi, G.: Multiobjective Evolution of Neural Controllers and Task Complexity. IEEE Transactions on Robotics 23(6), 1225–1234 (2007)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electric and Electronic Eng., University of Toyama, Toyama, Japan

    Genci Capi & Hideki Toda

  2. Toyama National College of Technology, Japan

    Shin-Ichiro Kaneko

Authors
  1. Genci Capi

    You can also search for this author inPubMed Google Scholar

  2. Hideki Toda

    You can also search for this author inPubMed Google Scholar

  3. Shin-Ichiro Kaneko

    You can also search for this author inPubMed Google Scholar

Editor information

Editors and Affiliations

  1. Democritus University of Thrace, 68200 N., Orestiada, Greece

    Lazaros Iliadis

  2. University of Central Greece, 35100, Lamia, Greece

    Ilias Maglogiannis

  3. Frederick University, 1036, Nicosia, Cyprus

    Harris Papadopoulos

Rights and permissions

Copyright information

© 2011 IFIP International Federation for Information Processing

About this paper

Cite this paper

Capi, G., Toda, H., Kaneko, SI. (2011). Real Time Robot Policy Adaptation Based on Intelligent Algorithms. In: Iliadis, L., Maglogiannis, I., Papadopoulos, H. (eds) Artificial Intelligence Applications and Innovations. EANN AIAI 2011 2011. IFIP Advances in Information and Communication Technology, vol 364. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23960-1_1

Download citation

Publish with us

[8]ページ先頭
©2009-2025 Movatter.jp