This is my reinforcement learning code. I went through four different algorithms to solve an example of navigating a maze.
The first three examples show an agent navigating a grid maze. It includes Value Iteration, Policy Iteration, and Q-Learning Images are provided to show the results.
The last example shows an agent moving towards a target. This includes Deep Q Learning. This is stored in the dqn folder.
I hope you find this code useful in learning how these algorithms work. I made many comments to demonstrate the different steps of the algorithm.
Value Iteration Result
Policy Iteration Result
Q Learning Values
