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.
- T. Balch. Teambots domain: Soccerbots, 2000. http://www-2.cs.cmu.edu/ trb/TeamBots/ Domains/SoccerBots.]]Google Scholar
- R. A. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2:14--23, 1986.]]Google ScholarCross Ref
- T. G. Dietterich. The MAXQ method for hierarchical reinforcement learning. In Proceedings of the Fifteenth International Conference on Machine Learning, 1998.]] Google ScholarDigital Library
- E. Gat. Three-layer architectures. Artificial Intelligence and Mobile Robots, pages 195--210. AAAI Press, Menlo Park, CA, 1998.]] Google ScholarDigital Library
- F. Gomez and R. Miikkulainen. Incremental evolution of complex general behavior. Adaptive Behavior, 5:317--342, 1997.]] Google ScholarDigital Library
- 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.]]Google Scholar
- 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.]] Google ScholarDigital Library
- 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.]]Google ScholarDigital Library
- L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4:237--285, May 1996.]]Google ScholarDigital Library
- 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.]]Google ScholarCross Ref
- 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.]]Google Scholar
- M. A. Potter and K. A. D. Jong. Cooperative coevolution: An architecture for evolving coadapted subcomponents. Evolutionary Computation, 8:1--29, 2000.]] Google ScholarDigital Library
- 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.]] Google ScholarDigital Library
- 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.]]Google ScholarCross Ref
- P. Stone. Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer. MIT Press, 2000.]] Google ScholarDigital Library
- 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.]] Google ScholarDigital Library
- 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.]] Google ScholarDigital Library
- P. Stone and R. S. Sutton. Keepaway soccer: a machine learning testbed. In RoboCup-2001: Robot Soccer World Cup V. Springer Verlag, Berlin, 2002.]] Google ScholarDigital Library
- P. Stone and M. Veloso. A layered approach to learning client behaviors in the RoboCup soccer server. Applied Artificial Intelligence, 12:165--188, 1998.]]Google ScholarCross Ref
- 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).]] Google ScholarDigital Library
- 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.]]Google ScholarDigital Library
- 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.]]Google Scholar
- 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.]] Google ScholarDigital Library
Index Terms
- Concurrent layered learning
Recommendations
Layered learning
ECML'00: Proceedings of the 11th European Conference on Machine LearningThis paper presents layered learning, a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is intractable with existing learning algorithms. Given a hierarchical task ...
The evolution of layered protocol stacks leads to an hourglass-shaped architecture
SIGCOMM '11: Proceedings of the ACM SIGCOMM 2011 conferenceThe Internet protocol stack has a layered architecture that resembles an hourglass. The lower and higher layers tend to see frequent innovations, while the protocols at the waist of the hourglass appear to be "ossified". We propose EvoArch, an abstract ...
The evolution of layered protocol stacks leads to an hourglass-shaped architecture
SIGCOMM '11The Internet protocol stack has a layered architecture that resembles an hourglass. The lower and higher layers tend to see frequent innovations, while the protocols at the waist of the hourglass appear to be "ossified". We propose EvoArch, an abstract ...
Comments