Skip to main content

Tutorial 4: From Reinforcement Learning to Planning

Difficulty level

In this tutorial, you will implement one of the simplest model-based reinforcement learning algorithms, Dyna-Q. You will understand what a world model is, how it can improve the agent's policy, and the situations in which model-based algorithms are more advantageous than their model-free counterparts.

Topics covered in this lesson
  • Implementing a model-based RL agent, Dyna-Q, that can solve a simple task
  • Investigating the effect of planning on the agent's behavior
  • Comparing the behaviors of a model-based and model-free agent in light of an environmental change

Experience with Python Programming Language

Back to the course