Table of Content

Table of Contents

1.0 Executive Summary
1.1 Research Scope
1.2 Research Methodology

2.0 Reinforced Learning – Introduction
2.1 Reinforcement Learning Focuses on Finding and Executing the Best Possible Method for a Predefined Goal
2.2 RL Systems Revolves Around an Agent that Navigates in the Environment According to the State to Achieve Rewards
2.3 Model-free RL Methods Rely on a Trial and Error Method to Find the Most Efficient Approach Toward Goal Fulfilment
2.4 Model-based RL Constructs an Internal Model and Simulates an Action to Determine Outcome and Transitions Before Taking Action
2.5 Reinforcement Learning is a Computationally Intensive Method of Machine Learning and Thus Finds Limited Application at Edge

3.0 Innovations and Companies to Action
3.1 Multiple Research Studies and Deployments by Leading Companies and Universities Have Accelerated the Commercialization of RL
3.2 Robotics Has Been an Early Use Case for Reinforcement Learning Systems
3.3 Self-driving Cars Can Leverage RL to Take Complex Decisions in a Dynamic Environment
3.4 RL Systems are Being Used to Design Gameplays and to Enable Realistic Simulations in Virtual Environments
3.5 A Wide Range of Use Cases Based on RL are Being Developed Across Industries

4.0 Growth Opportunity
4.1 The Practical Applications of Theoretical Research in the Area of RL Have to be Explored by Industry-academia Collaboration
4.2 RL Systems Can Be Relied Upon To Understand the Complex Interplay Between Multiple Elements of an Environment

5.0 Industry Contacts
5.1 Key Contacts
Legal Disclaimer