Reinforcement Learning (Self-Paced)

Upcoming Batches for Reinforcement Learning (Self-Paced)

Enroll Training Starting from Timing Location
No Batch Available Make an Enquiry

Course Description

In this course, you will be introduced to Reinforcement Learning, an area of Machine Learning. You will learn the Markov Decision Processes, Bandit Algorithms, Dynamic Programming, and Temporal Difference (TD) methods. You will be introduced to Value function, Bellman Equation, and Value iteration. You will also learn Policy Gradient methods. You will learn to make decisions in uncertain environment.


 

Introduction to Reinforcement Learning

  • Learning Objectives: The aim of this module is to introduce you to the fundamentals of Reinforcement Learning and its elements. This module also introduces you to OpenAI Gym - a programming environment used for implementing RL agents.

    Topics:

    • Branches of Machine Learning
    • What is Reinforcement Learning?
    • The Reinforcement Learning Process
    • Elements of Reinforcement Learning
    • RL Agent Taxonomy
    • Reinforcement Learning Problem
    • Introduction to OpenAI Gym

Bandit Algorithms and Markov Decision Process

  • Learning Objectives: The aim of this module is to learn Bandit Algorithms and Markov Decision Process.

    Topics:

    • Bandit Algorithms
    • Markov Process
    • Markov Reward Process
    • Markov Decision Process

Dynamic Programming & Temporal Difference Methods

  • Learning Objectives: The aim of this module is to develop an understanding of Dynamic Programming Algorithms and Temporal Difference Learning methods.

    Topics:

    • Introduction to Dynamic Programming
    • Dynamic Programming Algorithms
    • Monte Carlo Methods
    • Temporal Difference Learning Methods

Deep Q Learning

  • Learning Objectives: The aim of this module is to learn Policy Gradients and develop an understanding of Deep Q Learning

    Topics:

    • Policy Gradients
    • Policy Gradients using TensorFlow
    • Deep Q learning
    • Q learning with replay buffers, target networks, and CNN

In-class Project

  • Goal: The aim of this module is to provide you hands-on experience in Reinforcement Learning.

Prerequisite

Required Pre-requisites

  • Fundamentals in AI & ML, Probability, Python, Neural Networks, Frameworks, Deep Learning library like PyTorch/ Theano/ Tensorflow

Edureka offers you complimentary self-paced courses

  • Statistics and Machine learning algorithms
  • Python Essentials
Thumb

Available on Request

Principle Instructor

Who should take this course?

  • Web Developers
  • Software Developers
  • Programmers
  • Anyone who wants to learn reinforcement learning

Courses Category

Similar Courses