This repository contains a simple Markov Decision Process (MDP) example located in rl/mdp_board_pathfinding.py. The environment simulates an agent navigating a 2D grid from the top-left corner to the bottom-right corner while avoiding blocked cells and receiving a reward when it reaches the goal.

• Python 3.8 or later (only the standard library is used)

cd rl
python3 mdp_board_pathfinding.py
python3 mdp_board_pathfinding_q_function.py