This repository is a collection of reinforcement learning projects that I have worked on. The projects are implemented in Python using basic Python Libraries. The projects are based on the following algorithms:
- Q-Learning
- SARSA
The aim of the projects is to provide a basic understanding of reinforcement learning algorithms and how they can be implemented in Python.
The problem solved by the algorithm here is the Maze problem. The agent has to navigate through a maze to reach the goal. The agent can move in four directions: up, down, left, and right. The maze is represented as a grid where the agent can move to the next cell if it is not a wall.
The projects are implemented in Python 3.11. The following libraries are required to run the projects:
- numpy
- matplotlib
- tqdm
The output of the application are 3 graphs:
- The first graph shows the number of steps taken to reach the goal for each episode, on average, for each episode.
- The second graph shows the empty maze.
- The third graph shows the maze with the path taken by the agent to reach the goal.