Hands-on: CwCF using Deep-RL

This article presents the problem of CwCF and shows a practical usage of Deep-RL.

Let’s make an A3C: Implementation

This article shows how to implement the A3C algorithm in simple CartPole environment with Keras and TensorFlow in only 300 lines of code.

Let’s make an A3C: Theory

This article introduces Policy Gradient Methods and A3C algorithm.

Let’s make a DQN: Double Learning and Prioritized Experience Replay

In this article we will update our DQN agent with Double Learning and Priority Experience Replay, both substantially improving its performance and stability.

Let’s make a DQN: Full DQN

This article explains concepts of target network and error clipping to make a full DQN.

Let’s make a DQN: Debugging

In this article we will show how to track the learning and how to display the learned Q function in a form of a color map.

Let’s make a DQN: Implementation

In this article, we will implement an agent using Q-network to solve a cart pole balancing problem.

Let’s make a DQN: Theory

In this first article from series Let's make a DQN you will a learn about the theory behind Q-networks.