✦ LIBER ✦

A reinforcement learning approach based on the fuzzy min-max neural network

✍ Scribed by Aristidis Likas; Kostas Blekas

Publisher: Springer US
Year: 1996
Tongue: English
Weight: 374 KB
Volume: 4
Category: Article
ISSN: 1370-4621
DOI: 10.1007/bf00426025

No coin nor oath required. For personal study only.

✦ Synopsis

The fuzzy min-max neural network constitutes a neural architecture that is based on hyperbox fuzzy sets and can be incrementally trained by appropriately adjusting the number of hyperboxes and their corresponding volumes. Two versions have been proposed: for supervised and unsupervised learning. In this paper a modified approach is presented that is appropriate for reinforcement leaming problems with discrete action space and is applied to the difficult task of autonomous vehicle navigation when no a priori knowledge of the enivronment is available. Experimental results indicate that the proposed reinforcement learning network exhibits superior learning behavior compared to conventional reinforcement schemes.

📜 SIMILAR VOLUMES

Classifying Algorithm Based on a Fuzzy N

Classifying Algorithm Based on a Fuzzy Neural network for the control of a Network Attached Optical Jukebox

✍ Xuan Liu; Hui-bo Jia; Ming Cheng 📂 Article 📅 2006 🏛 Tianjin University of Technology 🌐 English ⚖ 436 KB

A new type of fuzzy neural network based

A new type of fuzzy neural network based on a truth space approach for automatic acquisition of fuzzy rules with linguistic hedges

✍ Shin-ichi Horikawa; Takeshi Furuhashi; Yoshiki Uchikawa 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 791 KB

Fuzzy reasoning methods are generally classified into two approaches: the direct approach and the truth space approach. Set,eral researches on the relationships between these approaches haL'e been reported. There has been, howeLrer, no research which discusses their utility. The authors haL~e preL,

A control strategy for leveling load pow

A control strategy for leveling load power fluctuations with a successive learning fuzzy-neural network based on prediction of average load power

✍ Toshinori Fujii; Shigeyuki Funabiki 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 957 KB

A neural network approach for the predic

A neural network approach for the prediction of the refractive index based on experimental data

✍ Alex Alexandridis; Eva Chondrodima; Konstantinos Moutzouris; Dimos Triantis 📂 Article 📅 2011 🏛 Springer 🌐 English ⚖ 689 KB

A modified learning algorithm for the mu

A modified learning algorithm for the multilayer neural network with multi-valued neurons based on the complex QR decomposition

✍ Igor Aizenberg; Antonio Luchetta; Stefano Manetti 📂 Article 📅 2011 🏛 Springer 🌐 English ⚖ 603 KB

A study of the emotional evaluation mode

A study of the emotional evaluation models of color patterns based on the adaptive fuzzy system and the neural network

✍ Jinsub Um; Kyoungbae Eum; Joonwhoan Lee 📂 Article 📅 2002 🏛 John Wiley and Sons 🌐 English ⚖ 968 KB

## Abstract Proposed in this article are two kinds of emotional models based on the neural network and the adaptive fuzzy system that can transform the physical features of a color pattern into its emotional features. The purpose of this system of models is to evaluate the neural network and adapti