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

@incollection{citeulike:1724117, 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.}, author = {Duan, Yong and Cui, Baoxia and Xu, Xinhe}, citeulike-article-id = {1724117}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-540-72393-6_21}, doi = {10.1007/978-3-540-72393-6_21}, journal = {Advances in Neural Networks – ISNN 2007}, keywords = {abstraction, continuous\_space, fuzzy, learning, neural\_network}, pages = {160--169}, posted-at = {2007-10-03 15:02:03}, priority = {3}, title = {State Space Partition for Reinforcement Learning Based on Fuzzy Min-Max Neural Network}, url = {http://dx.doi.org/10.1007/978-3-540-72393-6_21}, year = {2007} }

TY - CHAP ID - citeulike:1724117 L3 - citeulike-article-id:1724117 N2 - 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. JF - Advances in Neural Networks – ISNN 2007 EP - 169 TI - State Space Partition for Reinforcement Learning Based on Fuzzy Min-Max Neural Network SP - 160 KW - abstraction KW - continuous_space KW - fuzzy KW - learning KW - neural_network AU - Duan, Yong AU - Cui, Baoxia AU - Xu, Xinhe PY - 2007/// UR - http://dx.doi.org/10.1007/978-3-540-72393-6_21 ER -