Reinforcement Learning in Neural Networks: a Survey

Abstract

In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applications. Although many surveys investigated general RL, no survey is specifically dedicated to the combination of artificial neural networks and RL. This paper therefore describes the state of the art of NNRL algorithms, with a focus on robotics applications. In this paper, a comprehensive survey is started with a discussion on the concepts of RL. Then, a review of several different NNRL algorithms is presented. Afterwards, the performances of different NNRL algorithms are evaluated and compared in learning prediction and learning control tasks from an empirical aspect and the paper concludes with a discussion on open issues.

Authors and Affiliations

Ahmad Ghanbari| Faculty of Mechanical Engineering, and Mechatronics Research Laboratory, School of Engineering Emerging Technologies, University of Tabriz, Tabriz, Iran, Yasaman Vaghei| Mechatronics Research Laboratory, School of Engineering Emerging Technologies, University of Tabriz, Tabriz, Iran, Sayyed Mohammad Reza Sayyed Noorani| Mechatronics Research Laboratory, School of Engineering Emerging Technologies, University of Tabriz, Tabriz, Iran

Keywords

Related Articles

The Role of Climate and climatic factors on crop zoning agroclimatic sunflower cultivation in Hamedan province

Needs of human life from the beginning been an important factor We have been threatened by population growth, food security and human well- Men of science and technology with a new plan Maintain and improve their food...

Determination of Appropriate Land Use by Using Land Use Planning Process in Sykan Watershed of Ilam Province, Iran

Objective: The aim of this study is to provide a management plan for the Sykan watershed of Darre shahr city located in Ilam province using GIS in land use planning. Methods: For land using of Sykan watershed of Ilam p...

The Effect of Drying Kinetic on Shrinkage of Potato Slices

Objective: Potato is the fourth important food crop after wheat, rice and maize. Shrinkage of food materials has a negative consequence on the quality of the dehydrated product. The main objective pursued in this paper...

Interaction Effect of Salicylic Acid and Putrescine on Vase life of Cut Narcissus Flowers

The effects of salicylic acid (SA) and Putrescine (Put), on cut Narcissus was studied. SA (0, 100 and 200 mg l-1) and Put (0, 150 and 300 mg l-1), their combinations were tested as preservative mixture. This study was...

The Role of Climate in Sustainable Constructing Associated with Hot and Dry Area Architecture : Studied Case in Yazd Province

From 60 decade sustainability issues and sustainable developing have opened a way in scientific meetings associated with environment and urbanization and architecture. Sustainability goals are improving of environmen...

Download PDF file
  • EP ID EP13229
  • DOI -
  • Views 320
  • Downloads 12

How To Cite

Ahmad Ghanbari, Yasaman Vaghei, Sayyed Mohammad Reza Sayyed Noorani (2014). Reinforcement Learning in Neural Networks: a Survey. International journal of Advanced Biological and Biomedical Research, 2(5), 1398-1416. https://europub.co.uk/articles/-A-13229