This is an introductory Reinforcement Learning tutorial by JetBrains Academy demonstrating the approach on a simple task of solving a labyrinth.
You will implement a simple Q-learning algorithm that uses rewards and penalties and an iteratively updated Q-table to teach a learning agent find the shortest path through a 2D maze. You will get acquainted with the key concepts of RL and learn what kinds of problems such algorithms can be applied to and what limitations they carry.
The course includes building a dynamic visualization of the agent moving through the maze.
Have fun and good luck!
P.S. Want to contribute? Feel free to send a pull request to this course’s git repo.