An efficient mapping of fuzzy ART onto a neural architecture
Neural Networks
Reinforcement Learning
An Efficient Inductive Learning Method for Object-Oriented Database Using Attribute Entropy
IEEE Transactions on Knowledge and Data Engineering
SOS++: finding smart behaviors using learning and evolution
ICAL 2003 Proceedings of the eighth international conference on Artificial life
Fuzzy Q-Learning with the Modified ART Neural Network
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Self-Organizing Cognitive Agents and Reinforcement Learning in Multi-Agent Environment
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Modified ART 2A growing network capable of generating a fixed number of nodes
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
We propose a new method to categorize continuous numeric percepts for Q-learning, where percept vectors are classified into categories and Q-learning uses categories as states to acquire rules for agent behavior. In the proposed method, categories are represented by hyper-spheres. A percept vector is classified into a category that covers the vector and is the nearest from it. For efficient reinforcement learning, category merging is provided with the method, where the number of parameters to control category merging in the method is fewer than that in modified fuzzy ART. The proposed method is combined with Q-learning and it is compared with Q-learning with original and modified fuzzy ART. Experimental results show that our method learns good rules for agent behavior more effi- ciently than Q-learning with modified fuzzy ART.