State Space Partition for Reinforcement Learning Based on Fuzzy Min-Max Neural Network

Authors:
Yong Duan;Baoxia Cui;Xinhe Xu
Affiliations:
School of Information Science & Engineering, Shenyang University of Technology, Shenyang, 110023, China;School of Information Science & Engineering, Shenyang University of Technology, Shenyang, 110023, China;Institute of AI and Robotics, Northeastern University, Shenyang, 110004, China
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
Year:
2007

Citing 8
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
The Parti-game Algorithm for Variable Resolution Reinforcement Learning in Multidimensional State-spaces

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Adaptive Resolution Model-Free Reinforcement Learning: Decision Boundary Partitioning

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Q-Learning with Adaptive State Segmentation (QLASS)

CIRA '97 Proceedings of the 1997 IEEE International Symposium on Computational Intelligence in Robotics and Automation
Variable resolution discretization for high-accuracy solutions of optimal control problems

IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Adaptive state space partitioning for reinforcement learning

Engineering Applications of Artificial Intelligence
General fuzzy min-max neural network for clustering and classification

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a tabular reinforcement learning (RL) method is proposed based on improved fuzzy min-max (FMM) neural network. The method is named FMM-RL. The FMM neural network is used to segment the state space of the RL problem. The aim is to solve the "curse of dimensionality" problem of RL. Furthermore, the speed of convergence is improved evidently. Regions of state space serve as the hyperboxes of FMM. The minimal and maximal points of the hyperbox are used to define the state space partition boundaries. During the training of FMM neural network, the state space is partitioned via operations on hyperbox. Therefore, a favorable generalization performance of state space can be obtained. Finally, the method of this paper is applied to learn behaviors for the reactive robot. The experiment shows that the algorithm can effectively solve the problem of navigation in a complicated unknown environment.