Writing A Deep Reinforcement Learning Framework

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.

Start Course

Writing A Deep Reinforcement Learning Framework

Ready?

Writing A Deep Reinforcement Learning Framework

Core Functionality Of Our Framework

Why We Are Writing Our Own Framework

The Basic Design of our Framework

Writing our Network Classes

Writing the Memory Class

Writing our Epsilon Greedy Policy

Writing the Episode Loop Class

Writing the Agent Classes

Writing the Run File and Testing our DQN Agent

Restructuring Our Code Base

Coding Double and Dueling Deep Q Learning

Implementing Deep Deterministic Policy Gradients

Implementing Twin Delayed Deep Deterministic Policy Gradients

Implementing Soft Actor Critic

Code Cleanup Before We Proceed

Writing a Generic Replay Memory Buffer

Adding Multithreading to our Framework

Adding PPO

Adding Prioritized Experience Replay

Our Framework Now Has a Name

About the teacher

phil