Deep learning

Deep Q-Networks (DQNs) resource

The DQN architecture has two neural nets, the Q network and the Target networks, and a component called Experience Replay. The Q network is the agent that is trained to produce the Optimal State-Action value.

Visit the following resources to learn more:

• A Practical Guide to Deep Q-Networks
• A Hands-On Introduction to Deep Q-Learning using OpenAI Gym in Python
• How are Neural networks used in Deep Q-Learning?

Video resources:

• Deep Q Learning w/ DQN - Reinforcement Learning
• Deep Q Learning is Simple with PyTorch