Skip to main content
SpringerLink
Log in

Agent architecture based on an interactive self-reflection classifier system

  • Original Article
  • Published:
Artificial Life and Robotics Aims and scope Submit manuscript

Abstract

This paper extends the learning classifier system (LCS) to introduce a mechanism for recognizing a current situation by determining a boundary between self and others, and investigates its capability through interaction with an agent. Intensive simulations for adapting to an interacting agent have revealed the following implications: (1) the proposed architecture adapts to an interacting agent more quickly and appropriately than the conventional LCS, and (2) our architecture keeps its adaptation to an interacting agent even when the agent changes its internal models before our architecture acquires it completely.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Takadama K, Shimohara K (2001) Interactive self-reflection and its architecture based on cellular automata. Artif Life Robotics 5:86–91

    Google Scholar 

  2. Shiose T, Sawaragi T, Katai O, et al. (2000) Learning is equal to participation: interactive acquisition of identity in a group. 5th International Symposium on Artificial Life and Robotics (AROB '2000), p 434–437

  3. Yamaguchi T (2000) Interactive self-reflection-based reinforcement learning for multiagent coordination. 5th International Symposium on Artificial Life and Robotics (AROB '2000), p 442–445

  4. Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, New York

    MATH  Google Scholar 

  5. Wilson, SW (1994) ZCS: a zeroth level classifier system. Evol Comput 2:1–18

    Google Scholar 

  6. Russell SJ, Norving P (1995) Artificial intelligence: a modern approach. Prentice-Hall, Englewood Cliffs

    Google Scholar 

  7. Holland JH (1985) Properties of the bucket brigade algorithm. 1st International Conference on Genetic Algorithms (ICGA '85), p 1–7

Download references

Author information

Authors and Affiliations

  1. Tokyo Institute of Technology, 4259 Nagatsuta-cho, Midori-ku, 226-8502, Yokohama, Japan

    Keiki Takadama

  2. Kyoto University, Kyoto, Japan

    Hiroyasu Inoue & Osamu Katai

  3. ATR Human Information Science Laboratories, Kyoto, Japan

    Keiki Takadama & Katsunori Shimohara

  4. ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan

    Michio Okada

Authors
  1. Keiki Takadama
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hiroyasu Inoue
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Katsunori Shimohara
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Michio Okada
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Osamu Katai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Keiki Takadama.

About this article

Cite this article

Takadama, K., Inoue, H., Shimohara, K. et al. Agent architecture based on an interactive self-reflection classifier system. Artif Life Robotics 5, 103–108 (2001). https://doi.org/10.1007/BF02481347

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02481347

Key words

Search

Navigation