Search

Browse Subject Areas

For Authors

Submit a Proposal

Deep Reinforcement Learning and Its Industrial Use Cases

AI for Real-World Applications

Edited by Shubham Mahajan, Pethuru Raj and Amit Kant Pandit
Copyright: 2024   |   Expected Pub Date:2024/08/30
ISBN: 9781394272556  |  Hardcover  |  
416 pages

One Line Description
This book serves as a bridge connecting the theoretical foundations of DRL with practical, actionable insights for implementing these technologies in a variety of industrial contexts, making it a valuable resource for professionals and enthusiasts at the forefront of technological innovation.

Audience
The book will be read by researchers, postgraduate students, and industry engineers in machine learning and artificial intelligence, as well as those in business and industry seeking to understand how DRL can be applied to solve complex industry-specific challenges and improve operational efficiency.

Description
Deep Reinforcement Learning (DRL) represents one of the most dynamic and impactful areas of research and development in the field of artificial intelligence. Bridging the gap between decision-making theory and powerful deep learning models, DRL has evolved from academic curiosity to a cornerstone technology driving innovation across numerous industries. Its core premise—enabling machines to learn optimal actions within complex environments through trial and error—has broad implications, from automating intricate decision processes to optimizing operations that were previously beyond the reach of traditional AI techniques.
“Deep Reinforcement Learning and its Industrial Use Cases: AI for Real-World Applications” is an essential guide for anyone eager to understand the nexus between cutting-edge artificial intelligence techniques and practical industrial applications. This book not only demystifies the complex theory behind deep reinforcement learning (DRL) but also provides a clear roadmap for implementing these advanced algorithms in a variety of industries to solve real-world problems. Through a careful blend of theoretical foundations, practical insights, and diverse case studies, the book offers a comprehensive look into how DRL is revolutionizing fields such as finance, healthcare, manufacturing, and more, by optimizing decisions in dynamic and uncertain environments.
This book distills years of research and practical experience into accessible and actionable knowledge. Whether you’re an AI professional seeking to expand your toolkit, a business leader aiming to leverage AI for competitive advantage, or a student or academic researching the latest in AI applications, this book provides valuable insights and guidance. Beyond just exploring the successes of DRL, it critically examines challenges, pitfalls, and ethical considerations, preparing readers to not only implement DRL solutions but to do so responsibly and effectively.

Back to Top
Author / Editor Details
Shubham Mahajan, PhD, is an assistant professor in the School of Engineering at Ajeekya D Y Patil University, Pune, Maharashtra, India. He has eight Indian, one Australian, and one German patent to his credit in artificial intelligence and image processing. He has authored/co-authored more than 50 publications including peer-reviewed journals and conferences. His main research interests include image processing, video compression, image segmentation, fuzzy entropy, and nature-inspired computing methods with applications in optimization, data mining, machine learning, robotics, and optical communication.

Pethura Raj, PhD, is chief architect and vice president at Reliance Jio Platforms Ltd in Bangalore, India. He has a PhD in computer science and automation from the Indian Institute of Science in Bangalore, India. His areas of interest focus on artificial intelligence, model optimization, and reliability engineering. He has published thirty research papers and edited forty-two books.

Amit Kant Pandit, PhD, is an associate professor in the School of Electronics & Communication Engineering Shri Mata Vaishno Devi University, India. He has authored/co-authored more than 60 publications including peer-reviewed journals and conferences. He has two Indian and one Australian patent to his credit in artificial intelligence and image processing. His main research interests are image processing, video compression, image segmentation, fuzzy entropy, and nature-inspired computing methods with applications in optimization.

Back to Top

Table of Contents
Preface
1. Deep Reinforcement Learning Applications in Real-World Scenarios: Challenges and Opportunities
Sunilkumar Ketineni and Sheela J.
1.1 Introduction
1.1.1 Problems with Real-World Implementation
1.2 Application to the Real World
1.2.1 Security and Robustness
1.2.2 Generalization
1.2.2.1 Overcoming Challenges in DRL
1.3 Possibilities for Making a Difference in the Real World
1.3.1 Transfer Learning and Domain Adaptation
1.4 Meta-Learning
1.5 Deep Reinforcement Learning (DRL)
1.5.1 Hybrid Approaches
1.6 Online vs. Offline Reinforcement Learning
1.7 Human-in-the-Loop Systems
1.8 Benchmarking and Standardization
1.9 Collaborative Multi-Agent Systems
1.10 Transfer Learning and Domain Adaptation
1.11 Hierarchical and Multimodal Learning
1.12 Imitation Learning and Human Feedback
1.13 Inverse Reinforcement Learning
1.14 Sim-to-Real Transfer
1.15 Conclusion
References
2. Deep Reinforcement Learning: A Key to Unlocking the Potential of Robotics
and Autonomous Systems
Saksham and Chhavi Rana
2.1 Introduction
2.1.1 Significance of DRL Field
2.1.2 Transformative Advantages of DRL Field
2.2 Fields of Investigation
2.2.1 General Methods for Investigation
2.3 Background
2.3.1 Fundamentals of Deep Reinforcement Learning (DRL)
2.4 Deep Reinforcement Learning (DRL) in Robot Control
2.4.1 Navigation and Localization
2.4.2 Object Manipulation
2.5 Applications and Case Studies
2.6 Challenges and Future Directions
2.7 Evaluation and Metrics
2.8 Summary
References
3. Deep Reinforcement Learning Algorithms: A Comprehensive Overview
Shweta V. Bondre, Bhakti Thakre, Uma Yadav and Vipin D. Bondre
3.1 Introduction
3.1.1 How Reinforcement Learning Works?
3.2 Reinforcement Learning Algorithms
3.2.1 Value-Based Algorithms
3.2.1.1 Q-Learning
3.2.1.2 Deep Q-Networks (DQN)
3.2.1.3 Double DQN
3.2.1.4 Dueling DQN
3.3 Policy-Based
3.3.1 Policy Gradient Methods
3.3.2 REINFORCE (Monte Carlo Policy Gradient)
3.3.3 Actor–Critic Methods
3.3.4 Natural Policy Gradient Methods
3.4 Model-Based Reinforcement Learning
3.4.1 Probabilistic Ensembles with Trajectory Sampling (PETS)
3.4.2 Probabilistic Inference for Learning Control (PILCO)
3.4.3 Model Predictive Control (MPC)
3.4.4 Model-Agnostic Meta-Learning (MAML)
3.4.5 Soft Actor–Critic with Model Ensemble
3.4.6 Deep Deterministic Policy Gradients with Model (DDPG with Model)
3.5 Characteristics of Reinforcement Learning
3.6 DRL Algorithms and Their Advantages and Drawbacks
3.7 Conclusion
References
4. Deep Reinforcement Learning in Healthcare and Biomedical Applications
Balakrishnan D., Aarthy C., Nandhagopal Subramani, Venkatesan R. and Logesh T. R.
4.1 Introduction
4.2 Related Works
4.3 Deep Reinforcement Learning Framework
4.4 Deep Reinforcement Learning Applications in Healthcare and Biomedicine
4.5 Deep Reinforcement Learning Employs Efficient Algorithms
4.5.1 Deep Q-Networks
4.5.2 Policy Differentiation Techniques
4.5.3 Hindsight Experience Replay (HER)
4.5.4 Curiosity-Driven Exploration
4.5.5 Long Short-Term Memory Networks and Recurring Neural Network Designs
4.5.6 Multi-Agent DRL
4.6 Semi-Autonomous Control Based on Deep Reinforcement Learning for Robotic Surgery
4.6.1 Double Deep Q-Network (DDQN)
4.6.2 Materials and Methods
4.6.3 Results
4.6.4 Discussion
4.7 Conclusion
References
5. Application of Deep Reinforcement Learning in Adversarial Malware Detection
Manju and Chhavi Rana
5.1 Introduction
5.1.1 Background
5.1.2 Significance of Malware Detection
5.1.3 Challenges with Adversarial Attacks
5.2 Foundations of Deep Reinforcement Learning
5.2.1 Overview of Deep Reinforcement Learning
5.2.2 Core Concepts and Components
5.2.3 Relevance to Malware Detection
5.3 Malware Detection Landscape
5.3.1 Evolution of Malware Detection Techniques
5.3.2 Adversarial Attacks in Cybersecurity
5.3.3 Need for Advanced Detection Strategies
5.4 Deep Reinforcement Learning Techniques
5.4.1 Application of Deep Learning in Malware Detection
5.4.2 Reinforcement Learning Algorithms
5.5 Feature Selection Strategies
5.5.1 Importance of Feature Selection in Malware Detection
5.5.2 Techniques for Feature Selection
5.5.3 Optimization for Deep Reinforcement Learning Models
5.6 Datasets and Evaluation
5.7 Generating Adversarial Samples
Conclusion and Future Directions
Future Directions
References
6. Artificial Intelligence in Blockchain and Smart Contracts for Disruptive
Innovation
Eashwar Sivakumar, Kiran Jot Singh and Paras Chawla
6.1 Introduction
6.1.1 Smart Contract
6.2 Literature Review
6.2.1 Blockchain and Smart Contracts in Digital Identity
6.2.2 Blockchain and Smart Contracts in Financial Security
6.2.3 Blockchain and Smart Contracts in Supply Chain Management
6.2.4 Blockchain and Smart Contracts in Insurance
6.2.5 Blockchain and Smart Contracts in Healthcare
6.2.6 Blockchain and Smart Contracts in Agriculture
6.2.7 Blockchain and Smart Contracts in Real Estate
6.2.8 Blockchain and Smart Contracts in Education and Research
6.2.9 Blockchain and Smart Contracts in Other Sectors
6.3 Critical Analysis of the Review
6.4 Blockchain and Artificial Intelligence
6.5 Discussion on the Reasoning for Implementation of Blockchain
6.6 Conclusion
References
7. Clinical Intelligence: Deep Reinforcement Learning for Healthcare and Biomedical Advancements
Keerthika K., Kannan M. and T. Saravanan
7.1 Introduction
7.2 Deep Reinforcement Learning Methods
7.2.1 Model-Free Methods
7.2.2 Policy Gradient Methods
7.2.3 Model-Based Methods
7.3 Applications of DRL in Healthcare
7.3.1 Tailored Treatment Recommendations
7.3.2 Optimization of Clinical Trials
7.3.3 Disease Diagnosis Support
7.3.4 Accelerated Drug Discovery and Design
7.3.5 Enhanced Robotic Surgery and Assistance
7.3.6 Health Management System
7.4 Challenges
7.5 Healthcare Data Types
7.5.1 Electronic Healthcare Records (EHRs)
7.5.2 Laboratory Data
7.5.3 Sensor Data
7.5.4 Biomedical Imaging Information
7.6 Guidelines for the Application of DRL
7.7 A Case Study: DRL in Healthcare and Biomedical Applications
7.7.1 Optimizing Radiation Therapy Dose Distribution in Cancer Treatment
7.7.2 Dose Strategy Model in Sepsis Patient Treatment
References
8. Cultivating Expertise in Deep and Reinforcement Learning Principles
Chilakalapudi Malathi and J. Sheela
8.1 Introduction
8.1.1 Reinforcement Learning’s Constituent Parts
8.1.2 Process of Markov Decisions (MDP)
8.1.3 Learning Reinforcement Methods
8.2 Intensive Learning Foundations
8.2.1 A Definition of Deep Learning
8.2.2 Deep Learning Elements
8.2.2.1 Different Kinds of Deep Learning Networks
8.3 Integrating Deep Learning and Reinforcement Learning
8.3.1 Deep Reinforcement Learning
8.3.2 Deep Reinforcement Learning Complexity Problems
Conclusion
References
9. Deep Reinforcement Learning in Healthcare and Biomedical Research
Shruti Agrawal and Pralay Mitra
9.1 Introduction
9.1.1 Reinforcement Learning
9.1.2 Deep Reinforcement Learning
9.2 Learning Methods in Bioinformatics with Applications in Healthcare and Biomedical Research
9.2.1 Protein Folding
9.2.2 Protein Docking
9.2.3 Protein–Ligand Binding
9.2.4 Binding Peptide Generation
9.2.5 Protein Design and Engineering
9.2.6 Drug Discovery and Development
9.3 Applications in Biological Data
9.3.1 Omics Data
9.3.2 Medical Imaging
9.3.3 Brain/Body–Machine Interfaces
9.4 Adaptive Treatment Approach in Healthcare
9.5 Diagnostic Tools in Healthcare and Biomedical Research
9.6 Scope of Deep Reinforcement Learning in Healthcare and Biomedical Applications
9.6.1 State and Action Space
9.6.2 Reward
9.6.3 Policy
9.6.4 Model Training
9.6.5 Exploration
9.6.6 Credit Assignment
9.7 Conclusions
References
10. Deep Reinforcement Learning in Robotics and Autonomous Systems
Uma Yadav, Shweta V. Bondre and Bhakti Thakre
10.1 Introduction
10.2 The Promise of Deep Reinforcement Learning (DRL) in Real-World Robotics
10.3 Preliminaries
10.4 Enhancing RL for Real-World Robotics
10.5 Reinforcement Learning for Various Robotic Applications
10.6 Problems Faced in RL for Robotics
10.7 RL in Robotics: Trends and Challenges
10.8 Conclusion
References
11. Diabetic Retinopathy Detection and Classification Using Deep Reinforcement Learning
H.R. Manjunatha and P. Sathish
11.1 Introduction
11.2 Literature Survey
11.3 Diabetic Retinopathy Detection and Classification
11.4 Result Analysis
11.5 Conclusion
References
12. Early Brain Stroke Detection Based on Optimized Cuckoo Search Using LSTM‑Gated Multi-Perceptron Neural Network
Anita Venaik, Asha A., Dhiyanesh B., Kiruthiga G., Shakkeera L. and Vinodkumar Jacob
12.1 Introduction
12.2 Literature Survey
12.2.1 Problem Statement
12.3 Proposed Methodology
12.3.1 Dataset Collection
12.3.2 Preprocessing
12.3.3 Genetic Feature Sequence Algorithm (GFSA)
12.3.4 Disease-Prone Factor (DPF)
12.3.5 Decision Tree-Optimized Cuckoo Search (DTOCS)
12.3.6 Long Short-Term Memory Gate Multilayer Perceptron Neural Network (LSTM-MLPNN)
12.4 Result and Discussion
12.4.1 Performance Matrix
12.5 Conclusion
References
13. Hybrid Approaches: Combining Deep Reinforcement Learning with Other Techniques
M. T. Vasumathi, Manju Sadasivan and Aurangjeb Khan
13.1 Introduction
13.1.1 Digital Twin—Introduction
13.1.2 Model of a Digital Twin
13.1.2.1 Steps Involved in Building a Digital Twin Prototype
13.1.3 Application Areas of Digital Twins
13.1.3.1 Digital Twin in Medical Field
13.1.3.2 Digital Twin in Smart City
13.1.3.3 Digital Twin in Sports
13.1.3.4 Digital Twin in Smart Manufacturing
13.2 Digital Twin Technologies
13.2.1 Data Acquisition and Sensors
13.2.2 Data Analytics and Machine Learning
13.2.3 Cloud Computing
13.2.4 Other Technologies
13.3 Integration of RL and Digital Twin
13.3.1 Motivation for Combining Digital Twin and RL
13.3.2 How RL Enhances Decision-Making Within Digital Twins
13.4 Challenges of Using RL in Digital Twins
13.5 Digital Twin Modeling with RL
13.6 Technology Underlying RL-Based Digital Twins
13.6.1 Integration of RL with Digital Twins in Four Stages
13.6.2 Tools and Libraries for Developing RL-Based Digital Twins
13.6.2.1 Simulation and Digital Twin Platforms
13.6.2.2 Reinforcement Learning Libraries
13.6.3 Integration with Existing Systems and IoT Devices for RL Deployment
13.6.3.1 Data Collection and Sensor Integration
13.6.3.2 Communication and Data Ingestion
13.6.3.3 Digital Twin Integration
13.6.3.4 RL Integration
13.6.3.5 Control and Actuation
13.6.3.6 Implementation of Feedback and Learning Process
13.6.3.7 Dashboard for Alert and Visualization
13.6.3.8 Ensuring the Security and Authentication
13.7 Industry-Specific Applications: A Case Study of DT in a Car Manufacturing Unit
13.7.1 IoT Components Required for Creating Digital Twin for the Manufacturing Unit
13.7.2 Architecture of the Proposed Digital Twin for Car Manufacturing Unit
13.7.3 Challenges and Opportunities in the Implementation of DTs for Car Manufacturing
13.8 Conclusion
References
14. Predictive Modeling of Rheumatoid Arthritis Symptoms: A High-Performance Approach Using HSFO-SVM and UNET-CNN
Anusuya V., Baseera A., Dhiyanesh B., Parveen Begam Abdul Kareem and Shanmugaraja P.
14.1 Introduction
14.1.1 Novelty of the Research
14.2 Related Work
14.2.1 Challenges and Problem Identification Factor
14.3 HSFO-SVM Based on LSTM-Gated Convolution Neural Network (LSTMG-CNN)
14.3.1 C-Score and Cross-Fold Validation
14.3.2 Honey Scout Forager Optimization
14.3.3 Feature Selection Using SVM
14.3.4 UNET-CNN Classification
14.4 Result and Discussion
14.5 Conclusion
References
15. Using Reinforcement Learning in Unity Environments for Training AI Agent
Geetika Munjal and Monika Lamba
15.1 Introduction
15.2 Literature Review
15.3 Machine Learning
15.3.1 Categorization of Machine Learning
15.3.1.1 Supervised Learning
15.3.1.2 Unsupervised Learning
15.3.1.3 Reinforcement Learning
15.3.2 Classifying on the Basis of Envisioned Output
15.3.2.1 Classification
15.3.2.2 Regression
15.3.2.3 Clustering
15.3.3 Artificial Intelligence
15.4 Unity
15.4.1 Unity Hub
15.4.2 Unity Editor
15.4.3 Inspector
15.4.4 Game View
15.4.5 Scene View
15.4.6 Hierarchy
15.4.7 Project Window
15.5 Reinforcement Learning and Supervised Learning
15.5.1 Positive Reinforcement
15.5.2 Negative Reinforcement
15.5.3 Model-Free and Model-Based RL
15.6 Proposed Model
15.6.1 Setting Up a Virtual Environment
15.6.2 Setting Up of the Environment
15.6.2.1 Creating and Allocating Scripts for the Environment
15.6.2.2 Creating a Goal for the Agent
15.6.2.3 Reward-Driven Behavior
15.7 Markov Decision Process
15.8 Model-Based RL
15.9 Experimental Results
15.9.1 Machine Learning Models Used for the Environments
15.9.2 PushBlock
15.9.3 Hallway
15.9.4 Screenshots of the PushBlock Environment
15.9.5 Screenshots of the Hallway Environment
15.10 Conclusion
References
16. Emerging Technologies in Healthcare Systems
Ravi Kumar Sachdeva, Priyanka Bathla, Samriti Vij, Dishika, Madhur Jain, Lokesh Kumar, G. S. Pradeep Ghantasala and Rakesh Ahuja
16.1 Introduction
16.2 Personalized Medicine
16.3 AI and ML in Healthcare Sector
16.3.1 AI in Medical Diagnosis
16.3.2 Drug Discovery
16.3.3 Personalized Treatment Plans
16.3.4 Pattern Matching or Trend Detection
16.4 Immunotherapy
16.4.1 Monoclonal Antibodies
16.4.2 Checkpoint Inhibitors
16.4.3 CAR-T Cell Therapy
16.5 Regenerative Medicine
16.6 Digital Health (Use of Technology in Healthcare)
16.6.1 Wearable Devices
16.6.2 Telemedicine
16.6.3 Electronic Health Records
16.7 Health Inequity
16.7.1 Health Disparity
16.7.2 Health Equity
16.8 Future Directions in Healthcare Research
16.9 Challenges and Recommendations for Advanced Level of Modern Healthcare Technologies
16.9.1 Challenges
16.9.2 Recommendations
16.10 Healthcare Sector in Developing and Underdeveloped Countries
16.10.1 Healthcare Sector in Developing Countries
16.10.2 Healthcare Sector in Underdeveloped Countries
16.11 Comparison of Recent Progress and Future Mentoring in Healthcare Using Technology
16.12 Conclusion
References
Index

Back to Top



Description
Author/Editor Details
Table of Contents
Bookmark this page