Open AccessJournal Article
Reinforcement Learning in Neural Networks: A Survey
Reads0
Chats0
TLDR
This paper describes the state of the art of NNRL algorithms, with a focus on robotics applications and a comprehensive survey is started with a discussion on the concepts of RL.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.read more
Citations
More filters
Neural Networks And Fuzzy Systems A Dynamical Systems Approach To Machine Intelligence
TL;DR: Neural networks and fuzzy systems a dynamical systems approach to machine intelligence helps people enjoy a good book with a cup of coffee in the afternoon, instead they juggled with some harmful virus inside their desktop computer.
Proceedings ArticleDOI
Target following for an autonomous underwater vehicle using regularized ELM-based reinforcement learning
TL;DR: Simulation results have shown that AUV successfully tracks and follows the moving target by the proposed method of an AUV using regularized extreme learning machine (RELM) based RL.
Journal ArticleDOI
A Review of Unsupervised Artificial Neural Networks with Applications
TL;DR: Unsupervised algorithms have become very useful tools in segmentation of Magnetic resonance images for detection of anomalies in the body systems and some of the areas of application include exploratory data, statistical, biomedical, industrial, financial and control analysis.
Journal ArticleDOI
Neural Network for the identification of a functional dependence using data preselection
TL;DR: The article describes how to apply a fitness (or a penalty) function directly to the data, before a neural network is trained, and demonstrates the new method on the kinematics control of a redundant 2D manipulator.
Proceedings ArticleDOI
The context-aware learning model: Reward-based and experience-based logistic regression backpropagation
Joohee Suh,Dean F. Hougen +1 more
TL;DR: The Context-Aware Learning Model (CALM) and two different learning algorithms, which combines logistic regression backpropagation in artificial neural networks with hyperbolic reward-based learning and CALM-rLRB, are introduced.
References
More filters
Book
Genetic algorithms in search, optimization, and machine learning
TL;DR: In this article, the authors present the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields, including computer programming and mathematics.
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Journal ArticleDOI
ANFIS: adaptive-network-based fuzzy inference system
TL;DR: The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference System implemented in the framework of adaptive networks.
Book
Dynamic Programming and Optimal Control
TL;DR: The leading and most up-to-date textbook on the far-ranging algorithmic methododogy of Dynamic Programming, which can be used for optimal control, Markovian decision problems, planning and sequential decision making under uncertainty, and discrete/combinatorial optimization.
Journal ArticleDOI
Technical Note : \cal Q -Learning
Chris Watkins,Peter Dayan +1 more
TL;DR: This paper presents and proves in detail a convergence theorem forQ-learning based on that outlined in Watkins (1989), showing that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.