Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
XCS and GALE: A Comparative Study of Two Learning Classifier Systems on Data Mining
IWLCS '01 Revised Papers from the 4th International Workshop on Advances in Learning Classifier Systems
Applications of Learning Classifier Systems
Applications of Learning Classifier Systems
Strong, Stable, and Reliable Fitness Pressure in XCS due to Tournament Selection
Genetic Programming and Evolvable Machines
Learning classifier system equivalent with reinforcement learning with function approximation
GECCO '05 Proceedings of the 7th annual workshop on Genetic and evolutionary computation
Standard and averaging reinforcement learning in XCS
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Classifier prediction based on tile coding
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Classifier fitness based on accuracy
Evolutionary Computation
An analysis of generalization in the xcs classifier system
Evolutionary Computation
Limits in long path learning with XCS
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII
IEEE Transactions on Evolutionary Computation
Learning classifier systems: a complete introduction, review, and roadmap
Journal of Artificial Evolution and Applications
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Learning classifier systems: a complete introduction, review, and roadmap
Journal of Artificial Evolution and Applications
Learning classifier system with average reward reinforcement learning
Knowledge-Based Systems
| Hi-index | 0.00 |
We analyze generalization and learning in XCS with gradient descent. At first, we show that the addition of gradient in XCS may slow down learning because it indirectly decreases the learning rate. However, in contrast to what was suggested elsewhere, gradient descent has no effect on the achieved generalization. We also show that when gradient descent is combined with roulette wheel selection, which is known to be sensitive to small values of the learning rate, the learning speed can slow down dramatically. Previous results reported no difference in the performance of XCS with gradient descent when roulette wheel selection or tournament selection were used. In contrast, we suggest that gradient descent should always be combined with tournament selection, which is not sensitive to the value of the learning rate. When gradient descent is used in combination with tournament selection, the results show that (i) the slowdown in learning is limited and (ii) the generalization capabilities of XCS are not affected.