Reinforcement Learning: An Introduction to the Technology
REPORT INCLUDES:
- A general framework for deep Reinforcement Learning (RL) – also known as a semi-supervised learning model in machine learning paradigm
- Assessing the breadth and depth of RL applications in real-world domains, including increased data efficiency and stability as well as multi-tasking
- Understanding of the RL algorithm from different aspects; and persuade the decision makers and researchers to put more efforts on RL research
CHAPTER 1 REINFORCEMENT LEARNING
Reasons for Doing This Report
Intended Audience
Introduction to Reinforcement Learning
Artificial Intelligence and Machine Learning
Four Main Types of Machine Learning
Reinforcement Learning vs. Supervised Learning vs. Unsupervised Learning
Approaches to Reinforcement Learning Algorithms
Characteristics of Reinforcement Learning
Market Dynamics
Drivers
Restraints
Opportunities
Challenges of Reinforcement Learning
Slower Interaction with Real Systems as Compared to Faster Simulated Environments
Higher Variance and Instability
Absence of Reproducibility Due to Lack of Standardized Benchmarks, Frameworks and Evaluation Metrics
Inappropriate Definition of Rewards, Actions and States
Lack of Generalization
Future Aspects of Reinforcement Learning
Future Applications of Reinforcement Learning Across Verticals
Resources Management in Computer Clusters
Traffic Light Control
Robotics
Web System Configuration
Chemistry
Personalized Recommendations
Bidding and Advertising
Games
Market Potential
Companies Working on Reinforcement Learning
BONSAI
DEEPMIND TECHNOLOGIES
MALUUBA INC.
MATHWORKS
Analyst Credentials
Related BCC Research Reports
CHAPTER 2 BIBLIOGRAPHY
Reasons for Doing This Report
Intended Audience
Introduction to Reinforcement Learning
Artificial Intelligence and Machine Learning
Four Main Types of Machine Learning
Reinforcement Learning vs. Supervised Learning vs. Unsupervised Learning
Approaches to Reinforcement Learning Algorithms
Characteristics of Reinforcement Learning
Market Dynamics
Drivers
Restraints
Opportunities
Challenges of Reinforcement Learning
Slower Interaction with Real Systems as Compared to Faster Simulated Environments
Higher Variance and Instability
Absence of Reproducibility Due to Lack of Standardized Benchmarks, Frameworks and Evaluation Metrics
Inappropriate Definition of Rewards, Actions and States
Lack of Generalization
Future Aspects of Reinforcement Learning
Future Applications of Reinforcement Learning Across Verticals
Resources Management in Computer Clusters
Traffic Light Control
Robotics
Web System Configuration
Chemistry
Personalized Recommendations
Bidding and Advertising
Games
Market Potential
Companies Working on Reinforcement Learning
BONSAI
DEEPMIND TECHNOLOGIES
MALUUBA INC.
MATHWORKS
Analyst Credentials
Related BCC Research Reports
CHAPTER 2 BIBLIOGRAPHY
LIST OF TABLES
Table 1: Reinforcement Learning vs. Supervised Learning vs. Unsupervised Learning
Table 2: Global Machine Learning Market, by Region, Through 2024
Table 1: Reinforcement Learning vs. Supervised Learning vs. Unsupervised Learning
Table 2: Global Machine Learning Market, by Region, Through 2024
LIST OF FIGURES
Figure 1: Reinforcement Learning Process
Figure 2: Reinforcement Learning Workflow
Figure 3: Artificial Intelligence vs. Machine Learning vs. Reinforcement Learning
Figure 4: Machine Learning Applications
Figure 5: Types of Machine Learning
Figure 6: Reinforcement Learning Market Dynamics
Figure 7: Global Machine Learning Market, by Region, 2018-2024
Figure 1: Reinforcement Learning Process
Figure 2: Reinforcement Learning Workflow
Figure 3: Artificial Intelligence vs. Machine Learning vs. Reinforcement Learning
Figure 4: Machine Learning Applications
Figure 5: Types of Machine Learning
Figure 6: Reinforcement Learning Market Dynamics
Figure 7: Global Machine Learning Market, by Region, 2018-2024