Mellouk A. (ed.) Advances in Reinforcement Learning

InTech, 2011, -482 p.Reinforcement Learning (RL) is oft en referred to as a branch of artificial intelligence and has been one of the central topics in a broad range of scientific fields for the last two decades. Understanding of RL is expected to provide a systematic understanding of adaptive behaviors, including simple classical and operant conditioning of animals as well as all complex social and economical human behaviors that are designed to maximize benefits; and is also useful in machine learning and robotics. RL aims to find an appropriate mapping from situations to actions in which a certain reward is maximized. It can be defined as a class of problem solving approaches in which the learner (agent) learns through a series of trial-and-error searches and delayed rewards. The purpose is to maximize not just the immediate reward, but also the cumulative reward in the long run, such that the agent can learn to approximate an optimal behavioral strategy by continuously interacting with the environment. This allows the agent to work in a previously unknown environment by learning about it gradually. Hence, it is closely related to various scientific domains as Optimization, Vision, Robotic and Control, Theoretical Computer Science, etc.
This book brings together many different aspects of the current research on several fields associated to Reinforcement Learning. Based on 24 Chapters, it covers a very broad variety of topics in Reinforcement Learning and their application in autonomous systems. A set of chapters in this book provide a general overview of RL while other chapters focus mostly on the applications of RL paradigms: Game Theory, Multi- Agent Theory, Robotic, Networking Technologies, Vehicular Navigation, Medicine and Industrial Logistic. Much of this work has been published in refereed journals and conference proceedings and these papers have been modified and edited for content and style.
This book shows that RL is a very dynamic area in terms of theory and application. The field of RL has been growing rapidly, producing a wide variety of learning algorithms for different applications. There is also a very extensive literature on RL, and to give a complete bibliography and a historical account of the research that led to the present form would have been impossible. It is thus inevitable that some topics have been treated in less detail than others.Wireless Networks Inductive Routing Based on Reinforcement Learning Paradigms
Cooperative Agent Learning Model in Multi-cluster Grid
A Reinforcement Learning Approach to Intelligent Goal Coordination of Two-Level Large-Scale Control Systems
Reinforcement Learning of User Preferences for a Ubiquitous Personal Assistant
Cooperative Behavior Rule Acquisition for Multi-Agent Systems by Machine Learning
Emergence of Intelligence Through Reinforcement Learning with a Neural Network
Reinforcement Learning using Kohonen Feature Map Probabilistic Associative Memory based on Weights Distribution
How to Recommend Preferable Solutions of a User in Interactive Reinforcement Learning?
Reward Prediction Error Computation in the Pedunculopontine Tegmental Nucleus Neurons
Subgoal Identifications in Reinforcement Learning: A Survey
A Reinforcement Learning System Embedded Agent with Neural Network-Based Adaptive Hierarchical Memory Structure
Characterization of Motion Forms of Mobile Robot Generated in Q-Learning Process
A Robot Visual Homing Model that Traverses Conjugate Gradient TD to a Variable λ TD and Uses Radial Basis Features
Complex-Valued Reinforcement Learning: A Context-based Approach for POMDPs
Adaptive PID Control of a Nonlinear Servomechanism Using Recurrent Neural Networks
Robotic Assembly Replanning Agent Based on Neural Network Adjusted Vibration Parameters
Integral Reinforcement Learning for Finding Online the Feedback Nash Equilibrium of Nonzero-Sum Differential Games
Online Gaming: Real Time Solution of Nonlinear Two-Player Zero-Sum Games Using Synchronous Policy Iteration
Hybrid Intelligent Algorithm for Flexible Job-Shop Scheduling Problem under Uncertainty
Adaptive Critic Designs-Based Autonomous Unmanned Vehicles Navigation: Application to Robotic Farm Vehicles
DAQL-Enabled Autonomous Vehicle Navigation in Dynamically Changing Environment
An Intelligent Marshaling Based on Transfer Distance of Containers Using a New Reinforcement Learning for Logistics
Distributed Parameter Bioprocess Plant Identification and I-Term Control Using Decentralized Fuzzy-Neural Multi-Models
Optimal Cardiac Pacing with Q Learning