Improving XCS Performance by Distribution
Learning Classifier Systems (LCSs) are rule-based evolutionary reinforcement learning (RL) systems. Today, especially variants of Wilson’s eXtended Classifier System (XCS) are widely applied for machine learning. Despite their widespread application, LCSs have drawbacks: The number of reinforcement cycles an LCS requires for learning largely depends on the complexity of the learning task. A straightforward way to reduce this complexity is to split the task into smaller sub-problems. Whenever this can be done, the performance should be improved significantly. In this paper, a nature-inspired multi-agent scenario is used to evaluate and compare different distributed LCS variants. Results show that improvements in learning speed can be achieved by cleverly dividing a problem into smaller learning sub-problems.
KeywordsNoise Signal Real Robot Emergent Behaviour Learn Classifier System Chicken Population
Unable to display preview. Download preview PDF.
- 1.Richter, U., Mnif, M., Branke, J., Müller-Schloer, C., Schmeck, H.: Towards a generic observer/controller architecture for Organic Computing. In: INFORMATIK 2006 – Informatik für Menschen!, pp. 112–119. Köllen Verlag (2006)Google Scholar
- 5.Barry, A.: Hierarchy formation within classifier systems – A review. In: Proceedings of the 1st International Conference on Evolutionary Algorithms an their Applications (EVCA 1996), Moscow, pp. 195–211 (1996)Google Scholar
- 6.Baneamoon, S.M., Salam, R.A., Talib, A.Z.H.: Learning process enhancement for robot behaviors. Int. Journal of Intelligent Technology 2(3), 172–177 (2007)Google Scholar
- 7.Dorigo, M.: Alecsys and the autonomouse: Learning to control a real robot by distributed classifier systems. Machine Learning 19(3), 209–240 (1995)Google Scholar
- 11.Mnif, M., Müller-Schloer, C.: Quantitative emergence. In: Proceedings of the 2006 IEEE Mountain Workshop on Adaptive and Learning Systems (IEEE SMCals 2006), pp. 78–84 (July 2006)Google Scholar
- 12.Richter, U., Mnif, M.: Learning to control the emergent behaviour of a multi-agent system. In: Proceedings of the 2008 Workshop on Adaptive Learning Agents and Multi-Agent Systems at AAMAS 2008 (ALAMAS+ALAg 2008), pp. 33–40 (May 2008)Google Scholar
- 13.Butz, M.V.: XCSJava 1.0: An implementation of the XCS classifier system in Java. Technical Report 2000027, Illinois Genetic Algorithms Laboratory (2000)Google Scholar