Welcome to the Maze Solver project repository! This project is all about navigating mazes comparing a Reinforcement Learning (RL) agent with the classic A* algorithm.
The main goal of this project is to explore and compare different approaches to solve mazes. I've implemented both an RL agent and the A* algorithm to see which one performs better in finding the optimal path through various mazes.
-
Reinforcement Learning Agent: We've trained an RL agent to learn how to navigate through mazes by exploring different paths, receiving rewards, and updating its strategy over time.
-
A Search Algorithm:* The classic A* algorithm, known for its efficiency and optimality, has been implemented to solve mazes. It cleverly combines heuristic estimation and intelligent search to find the shortest path from start to goal.
Even if they often make different paths, if trained enough, the RL and A* agents complete the maze with the same number of steps
- Clone the repository:
git clone https://github.com/agoniko/Path-Finding-Reinforcement-Learning.git- Install the required dependencies:
pip install -r requirements.txt
I welcome contributions, suggestions, and ideas to make this project even more enjoyable! If you have any exciting additions or improvements, please feel free to submit a pull request or open an issue. Let's make maze-solving even more fun together!
This project is open-source. You are free to use, modify, and distribute the code with proper attribution.
- Run the
path-finder.ipynbnotebook to start solving mazes.
