In this lesson we cover the fundamentals behind the interplay between an agent and its environment. This leads into the mathematical machinery of deep reinforcement learning.

Premium course

Value Functions and Action Value Functions

Premium course

Model Free vs. Model Based Learning

Premium course

Temporal Difference Learning

A Crash Course in Deep Learning

7 Lessons

Premium course

Dealing with Continuous State Spaces

Premium course

Naive Deep Q Learning in Code: Step 1 - Coding the Deep Q Network

Premium course

Naive Deep Q Learning in Code: Step 2 - Coding the Agent Class

Premium course

Naive Deep Q Learning in Code: Step 3 - Coding the Main Loop

Premium course

Naive Deep Q Learning in Code: Step 4 - Verifying Functionality

Premium course

Naive Deep Q Learning in Code: Step 5 - Analyzing our Agent's Performance

Premium course

Dealing with Screen Images with Covolutional Neural Networks

Deep Q Learning And All Its Variants

5 Chapters

Human Level Control Through Deep Reinforcement Learning

14 Lessons

Premium course

How to Read Deep Reinforcement Learning Papers

Premium course

How to Modify the OpenAI Gym Atari Environments

Premium course

How to Preprocess the OpenAI Gym Atari Screen Images

Premium course

How to Stack the Preprocessed Atari Screen Images

Premium course

How to Combine All the Changes

Premium course

How to Add Reward Clipping, Fire First, and No Ops

Premium course

How to Code the Agent's Memory

Premium course

How to Code the Deep Q Network

Premium course

Coding the Deep Q Agent: Step 1 - Coding the Constructor

Premium course

Coding the Deep Q Agent: Step 2 - Epsilon-Greedy Action Selection

Premium course

Coding the Deep Q Agent: Step 3 - Memory, Model Saving and Network Copying

Premium course

Coding the Deep Q Agent: Step 4 - The Agent's Learn Function

Premium course

Coding the Deep Q Agent: Step 5 - The Main Loop and Analyzing the Performance

Deep Reinforcement Learning with Double Q Learning

2 Lessons

Premium course

Coding the Double Q Learning Agent and Analyzing Performance

Dueling Network Architectures for Deep Reinforcement Learning

4 Lessons

Premium course

Coding the Dueling Deep Q Network

Premium course

Coding the Dueling Deep Q Learning Agent and Analyzing Performance

Premium course

Coding the Dueling Double Deep Q Learning Agent and Analyzing Performance

Improving Our Solutions

3 Lessons

Premium course

Implementing a Command Line Interface for Rapid Model Testing

Premium course

Consolidating Our Code Base for Maximum Extensability

Premium course

How to Test Our Agent and Watch it Play the Game in Real Time

Wrapping Up

1 Lesson

Premium course

Summarizing What We've Learned

Differences Between Tensorflow 2 and PyTorch

Premium course

Coding the Deep Q Network in Tensorflow 2

Premium course

Coding the Deep Q Learning Agent in Tensorflow 2

Premium course

Coding the DQN Agent Main Loop

Premium course

Coding the Tensorflow 2 Double Q Learning Agent

Premium course

Coding the Dueling Network in Tensorflow 2

Premium course

Coding the Dueling Double Deep Q Learning Agent in Tensorflow 2

Making our Virtual Environment

Premium course

Making our Agents Compatible with the New Gym Interface

About the teacher

phil

In 2012 I received my PhD in experimental condensed matter physics from West Virginia University. Following that I was a dry etch process engineer for Intel Corporation, where I leveraged big data to make essential process improvements for mission critical products. After leaving Intel in 2015, I have worked as a contract and freelance deep learning and artificial intelligence engineer.