Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Behavioral Cloning

Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_69



Behavioral cloning is a method by which human subcognitive skills can be captured and reproduced in a computer program. As the human subject performs the skill, his or her actions are recorded along with the situation that gave rise to the action. A log of these records is used as input to a learning program. The learning program outputs a set of rules that reproduce the skilled behavior. This method can be used to construct automatic control systems for complex tasks for which classical control theory is inadequate. It can also be used for training.

Motivation and Background

Behavioral cloning (Michie, Bain, & Hayes-Michie, 1990) is a form of learning by imitationwhose main motivation is to build a model of the behavior of a human when performing a complex skill. Preferably, the model should be in a readable form. It is related to other forms of...

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

Recommended Reading

  1. Abbeel, P., & Ng, A. Y. (2004). Apprenticeship learning via inverse reinforcement learning. In International conference on machine learning, Banff, Alberta, Canada. New York: ACM.Google Scholar
  2. Amit, R., & Matarić, M. (2002). Learning movement sequences from demonstration. In Proceedings of the second international conference on development and learning, Cambridge, MA, USA (pp. 203–208). Washington, D.C.: IEEE.Google Scholar
  3. Atkeson, C. G., & Schaal, S. (1997). Robot learning from demonstration. In D. H. Fisher (Ed.), Proceedings of the fourteenth international conference on machine learning, Nashville, TN, USA (pp. 12–20). San Francisco: Morgan Kaufmann.Google Scholar
  4. Bagnell, J. A., & Schneider, J. G. (2001). Autonomous helicopter control using reinforcement learning policy search methods. In International conference on robotics and automation, South Korea. IEEE Press, New York.Google Scholar
  5. Bratko, I., & Šuc, D. (2002). Using machine learning to understand operator’s skill. In Proceedings of the 15th international conference on industrial and engineering applications of artificial intelligence and expert systems (pp. 812–823). London: Springer. AAAI Press, Menlo Park, CA.Google Scholar
  6. Bratko, I., & Šuc, D. (2003). Learning qualitative models. AI Magazine, 24(4), 107–119.Google Scholar
  7. Chambers, R. A., & Michie, D. (1969). Man-machine co-operation on a learning task. In R. Parslow, R. Prowse, & R. Elliott-Green (Eds.), Computer graphics: techniques and applications. London: Plenum.Google Scholar
  8. Donaldson, P. E. K. (1960). Error decorrelation: A technique for matching a class of functions. In Proceedings of the third international conference on medical electronics (pp. 173–178).Google Scholar
  9. Hayes, G., & Demiris, J. (1994). A robot controller using learning by imitation. In Proceedings of the international symposium on intelligent robotic systems, Grenoble, France (pp. 198–204). Grenoble: LIFTA-IMAG.Google Scholar
  10. Hofmann, A. G., & Williams, B. C. (2006). Exploiting spatial and temporal flexiblity for plan execution of hybrid, under-actuated systems. In Proceedings of the 21st national conference on artficial intelligence, July 2006, Boston, MA (pp. 948–955).Google Scholar
  11. Isaac, A., & Sammut, C. (2003). Goal-directed learning to fly. In T. Fawcett & N. Mishra (Eds.), Proceedings of the twentieth international conference on machine learning, Washington, D.C. (pp. 258–265). Menlo Park: AAAI.Google Scholar
  12. Križman, V., & Džeroski, S. (1995). Discovering dynamics from measured data. Electrotechnical Review, 62(3–4), 191–198.Google Scholar
  13. Kuniyoshi, Y., Inaba, M., & Inoue, H. (1994). Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation, 10, 799–822.Google Scholar
  14. Michie, D., Bain, M., & Hayes-Michie, J. E. (1990). Cognitive models from subcognitive skills. In M. Grimble, S. McGhee, & P. Mowforth (Eds.), Knowledge-based systems in industrial control. Stevenage: Peter Peregrinus.Google Scholar
  15. Ng, A. Y., Jin Kim, H., Jordan, M. I., & Sastry, S. (2003). Autonomous helicopter flight via reinforcement learning. In S. Thrun, L. Saul, & B. Schölkopf (Eds.), Advances in neural information processing systems 16. Cambridge: MIT Press.Google Scholar
  16. Ng, A. Y., & Russell, S. (2000). Algorithms for inverse reinforcement learning. In Proceedings of 17th international conference on machine learning, Stanford, CA, USA (pp. 663–670). San Francisco: Morgan Kaufmann.Google Scholar
  17. Pomerleau, D. A. (1989). ALVINN: An autonomous land vehicle in a neural network. In D. S. Touretzky (Ed.), Advances in neural information processing systems. San Mateo: Morgan Kaufmann.Google Scholar
  18. Potts, D., & Sammut, C. (November 2005). Incremental learning of linear model trees. Machine Learning, 6(1–3), 5–48.Google Scholar
  19. Sammut, C., Hurst, S., Kedzier, D., & Michie, D. (1992). Learning to fly. In D. Sleeman & P. Edwards (Eds.), Proceedings of the ninth international conference on machine learning, Aberdeen (pp. 385–393). San Francisco: Morgan Kaufmann.Google Scholar
  20. Šuc, D., & Bratko, I. (1997). Skill reconstruction as induction of LQ controllers with subgoals. In IJCAI-97: Proceedings of the fiftheenth international joint conference on artificial intelligence, Nagoya, Japan (Vol. 2, pp. 914–920). San Francisco: Morgan Kaufmann.Google Scholar
  21. Šuc, D., & Bratko, I. (1999a). Modelling of control skill by qualitative constraints. In Thirteenth international workshop on qualitative reasoning, 7–9 June 1999, Lock Awe, Scotland (pp. 212–220). Aberystwyth: University of Aberystwyth.Google Scholar
  22. Šuc, D., & Bratko, I. (1999b). Symbolic and qualitative reconstruction of control skill. Electronic Transactions on Artificial Intelligence, 3(B), 1–22.MathSciNetGoogle Scholar
  23. Urbančič, T., & Bratko, I. (1994). Reconstructing human skill with machine learning. In A. Cohn (Ed.), Proceedings of the 11th European conference on artificial intelligence. Wiley. Amsterdam: New York.Google Scholar
  24. Widrow, B., & Smith, F. W. (1964). Pattern recognising control systems. In J. T. Tou & R. H. Wilcox (Eds.), Computer and information sciences. London: Clever Hume.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

There are no affiliations available