Course Outline


  • Learning through positive reinforcement

Elements of Reinforcement Learning

Important Terms (Actions, States, Rewards, Policy, Value, Q-Value, etc.)

Overview of Tabular Solutions Methods

Creating a Software Agent

Understanding Value-based, Policy-based, and Model-based Approaches

Working with the Markov Decision Process (MDP)

How Policies Define an Agent's Way of Behaving

Using Monte Carlo Methods

Temporal-Difference Learning

n-step Bootstrapping

Approximate Solution Methods

On-policy Prediction with Approximation

On-policy Control with Approximation

Off-policy Methods with Approximation

Understanding Eligibility Traces

Using Policy Gradient Methods

Summary and Conclusion


  • Experience with machine learning
  • Programming experience


  • Data scientists
  21 Hours


Related Courses

Introduction to Data Science and AI using Python

  35 hours

AI in Digital Marketing

  7 hours

Artificial Intelligence (AI) for Managers

  7 hours

AI in business and Society & The future of AI - AI/Robotics

  7 hours

Genetic Algorithms

  28 hours

Intelligent Testing

  14 hours

Artificial Intelligence (AI) for Robotics

  21 hours

AI and Robotics for Nuclear - Extended

  120 hours

AI and Robotics for Nuclear

  80 hours

AI-100: Designing & Implementing Azure AI Solutions- AI-100T01-A

  28 hours

Deep Reinforcement Learning with Python

  21 hours

Reinforcement Learning with Java

  21 hours

IBM Cloud Pak for Data

  14 hours

OptaPlanner in Practice

  21 hours

UiPath for Intelligent Process Automation (IPA)

  14 hours