Encyclopedia of Machine Learning

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

Adaptive Real-Time Dynamic Programming

  • Andrew G. Barto
Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_10



Adaptive Real-Time Dynamic Programming (ARTDP) is an algorithm that allows an agent to improve its behavior while interacting over time with an incompletely known dynamic environment. It can also be viewed as a heuristic search algorithm for finding shortest paths in incompletely known stochastic domains. ARTDP is based on Dynamic Programming (DP), but unlike conventional DP, which consists of off-line algorithms, ARTDP is an on-line algorithm because it uses agent behavior to guide its computation. ARTDP is adaptive because it does not need a complete and accurate model of the environment but learns a model from data collected during agent-environment interaction. When a good model is available, Real-Time Dynamic Programming (RTDP) is applicable, which is ARTDP without the model-learning component.

Motivation and Background

RTDP combines strengths of heuristic search and DP. Like heuristic search – and unlike conventional DP – it does not have to evaluate the...

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

Recommended Reading

  1. Barto, A., Bradtke, S., & Singh, S. (1995). Learning to act using real-time dynamic programming. Artificial Intelligence, 72(1–2), 81–138.Google Scholar
  2. Bertsekas, D., & Tsitsiklis, J. (1989). Parallel and distributed computation: Numerical methods. Englewood Cliffs, NJ: Prentice-Hall.zbMATHGoogle Scholar
  3. Bonet, B., & Geffner, H. (2003a). Labeled RTDP: Improving the convergence of real-time dynamic programming. In Proceedings of the 13th international conference on automated planning and scheduling (ICAPS-2003). Trento, Italy.Google Scholar
  4. Bonet, B., & Geffner, H. (2003b). Faster heuristic search algorithms for planning with uncertainty and full feedback. In Proceedings of the international joint conference on artificial intelligence (IJCAI-2003). Acapulco, Mexico.Google Scholar
  5. Feng, Z., Hansen, E., & Zilberstein, S. (2003). Symbolic generalization for on-line planning. In Proceedings of the 19th conference on uncertainty in artificial intelligence. Acapulco, Mexico.Google Scholar
  6. Hansen. E., & Zilberstein, S. (2001). LAO*: A heuristic search algorithm that finds solutions with loops. Artificial Intelligence, 129, 35–62.zbMATHMathSciNetGoogle Scholar
  7. Jalali, A., & Ferguson, M. (1989). Computationally efficient control algorithms for Markov chains. In Proceedings of the 28th conference on decision and control (pp.1283–1288), Tampa, FL.Google Scholar
  8. Korf, R. (1990). Real-time heuristic search. Artificial Intelligence, 42(2–3), 189–211.zbMATHGoogle Scholar
  9. Smith, T., & Simmons, R. (2006). Focused real-time dynamic programming for MDPs: Squeezing more out of a heuristic. In Proceedings of the national conference on artificial intelligence (AAAI). Boston, MA: AAAI Press.Google Scholar
  10. Sutton, R. (1990). Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In Proceedings of the 7th international conference on machine learning (pp.216–224). San Mateo, CA: Morgan Kaufmann.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Andrew G. Barto

There are no affiliations available