PyTorch Reinforcement Learning Tutorials

This page provides an overview of the PyTorch tutorials related to reinforcement learning (RL). RL is a subset of machine learning that focuses on how agents learn to make decisions in an environment to maximize some notion of cumulative reward.

Getting Started

If you are new to PyTorch and RL, we recommend starting with the following tutorials:

• PyTorch Basics
• Reinforcement Learning Basics

Tutorials

Here are some of the key tutorials on PyTorch RL:

• Policy Gradient Methods
• Deep Q-Networks (DQN)
• Proximal Policy Optimization (PPO)
• Asynchronous Advantage Actor-Critic (A3C)

Images

Here is an image of a classic RL environment, the CartPole:

Further Reading

For more in-depth reading, check out the following resources:

• PyTorch RL Documentation
• OpenAI Gym for a variety of RL environments