Concurrent layered learning

ABSTRACT

Hierarchies are powerful tools for decomposing complex control tasks into manageable subtasks. Several hierarchical approaches have been proposed for creating agents that can execute these tasks. Layered learning is such a hierarchical paradigm that relies on learning the various subtasks necessary for achieving the complete high-level goal. Layered learning prescribes training low-level behaviors (those closer to the environmental inputs) prior to high-level behaviors. In past implementations these lower-level behaviors were always frozen before advancing to the next layer. In this paper, we hypothesize that there are situations where layered learning would work better were the lower layers allowed to keep learning concurrently with the training of subsequent layers, an approach we call concurrent layered learning. We identify a situation where concurrent layered learning is beneficial and present detailed empirical results verifying our hypothesis. In particular, we use neuro-evolution to concurrently learn two layers of a layered learning approach to a simulated robotic soccer keepaway task. The main contribution of this paper is evidence that there exist situations where concurrent layered learning outperforms traditional layered learning. Thus, we establish that, when using layered learning, the concurrent training of layers can be an effective option.

References

1. T. Balch. Teambots domain: Soccerbots, 2000. http://www-2.cs.cmu.edu/ trb/TeamBots/ Domains/SoccerBots.]]
2. R. A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2:14--23, 1986.]]
3. T. G. Dietterich. The MAXQ method for hierarchical reinforcement learning. In Proceedings of the Fifteenth International Conference on Machine Learning, 1998.]]
4. E. Gat. Three-layer architectures. Artificial Intelligence and Mobile Robots, pages 195--210. AAAI Press, Menlo Park, CA, 1998.]]
5. F. Gomez and R. Miikkulainen. Incremental evolution of complex general behavior. Adaptive Behavior, 5:317--342, 1997.]]
6. F. Gomez and R. Miikkulainen. Learning robust nonlinear control with neuroevolution. Technical Report AI01-292, The University of Texas at Austin Department of Computer Sciences, 2001.]]
7. T. Haynes and S. Sen. Evolving behavioral strategies in predators and prey. In Adaptation and Learning in Multiagent Systems, pages 113--126. Springer Verlag, Berlin, 1996.]]
8. W. H. Hsu and S. M. Gustafson. Genetic programming and multi-agent layered learning by reinforcements. In Genetic and Evolutionary Computation Conference, New York,NY, July 2002.]]
9. L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237--285, May 1996.]]
10. I. Noda, H. Matsubara, K. Hiraki, and I. Frank. Soccer server: A tool for research on multiagent systems. Applied Artificial Intelligence, 12:233--250, 1998.]]
11. A. D. Pietro, L. While, and L. Barone. Learning in RoboCup keepaway using evolutionary algorithms. In GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, pages 1065--1072, New York, 9-13 July 2002.]]
12. M. A. Potter and K. A. D. Jong. Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation, 8:1--29, 2000.]]
13. C. D. Rosin and R. K. Belew. Methods for competitive co-evolution: Finding opponents worth beating. In Proceedings of the Sixth International Conference on Genetic Algorithms, pages 373--380, San Mateo,CA, July 1995. Morgan Kaufman.]]
14. J. D. Schaffer, D. Whitley, and L. J. Eshelman. Combinations of genetic algorithms and neural networks: A survey of the state of the art. In International Workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN-92), pages 1--37. IEEE Computer Society Press, 1992.]]
15. P. Stone. Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer. MIT Press, 2000.]]
16. P. Stone, (ed.), M. Asada, T. Balch, M. Fujita, G. Kraetzschmar, H. Lund, P. Scerri, S. Tadokoro, and G. Wyeth. Overview of RoboCup-2000. In RoboCup-2000: Robot Soccer World Cup IV. Springer Verlag, Berlin, 2001.]]
17. P. Stone and R. S. Sutton. Scaling reinforcement learning toward RoboCup soccer. In Proceedings of the Eighteenth International Conference on Machine Learning, pages 537--544. Morgan Kaufmann, San Francisco, CA, 2001.]]
18. P. Stone and R. S. Sutton. Keepaway soccer: a machine learning testbed. In RoboCup-2001: Robot Soccer World Cup V. Springer Verlag, Berlin, 2002.]]
19. P. Stone and M. Veloso. A layered approach to learning client behaviors in the RoboCup soccer server. Applied Artificial Intelligence, 12:165--188, 1998.]]
20. P. Stone and M. Veloso. Layered learning. In Machine Learning: ECML 2000, pages 369--381. Springer Verlag, Barcelona,Catalonia,Spain, May/June 2000. Proceedings of the Eleventh European Conference on Machine Learning (ECML-2000).]]
21. S. Whiteson, N. Kohl, R. Miikkulainen, and P. Stone. Evolving robocup keepaway players through task decomposition. In GECCO 2003: Proceedings of the Genetic and Evolutionary Computation Conference, July 2003. To appear.]]
22. D. Whitley, K. Mathias, and P. Fitzhorn. Delta-Coding: An iterative search strategy for genetic algorithms. In Proceedings of the Fourth International Conference on Genetic Algorithms, pages 77--84, 1991.]]
23. C. H. Yong and R. Miikkulainen. Cooperative coevolution of multi-agent systems. Technical Report AI01-287, The University of Texas at Austin Department of Computer Sciences, 2001.]]

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Control methods

    • Search methodologies

  • Machine learning

    • Machine learning approaches

      • Neural networks

• Theory of computation

  • Design and analysis of algorithms

    • Algorithm design techniques

      • Dynamic programming