Tensorflow Neural Networks using Deep Q-Learning Techniques

Offered By
Coursera Project Network
In this Guided Project, you will:

Utilize OpenAI Gym for model training.

Construct and train a Neural Network in Tensorflow using Q-Learning techniques

 Improve Q-Learning techniques with enhancements such as Dueling Q and Prioritized Experience Replay (PER).

Clock2 hours
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

By the end of this project you will learn how to train a reinforcement learning agent to play Atari video games autonomously using Deep Q-Learning with Tensorflow and OpenAI's Gym API. This project will familiarize you with the Gym interface and the process of training a Tensorflow-based neural network using Deep Q-Learning techniques. The methods you will learn in the course of this project will enable you to build reinforcement learning agents for any potential purpose and provide valuable experience in your Machine Learning and Artificial Intelligence development journey. Python experience is heavily recommended. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Artificial Intelligence (AI)Intelligent AgentUnsupervised LearningTensorflowReinforcement Learning

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Overview of Q-Learning Agents, Tensorflow, and OpenAI Gym

  2. Understand Deep-Q Learning Theory

  3. Building a Tensorflow Model

  4. Understand Activation Functions and Model Input

  5. Describe Keras Initializers and Optimizers

  6. Write Memory, Policy, and Action Functions

  7. Write The Training Function

  8. Explore Enhancements such as Double Q, Dueling Q, and Prioritized Experience Replay

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.