Solve-the-Gridworld-Problem-with-Reinforcement-Learning-Cont.

Based on the book --- Reinforcement Learning: An Introduction (2nd ed, 2018) by Sutton and Barto

For the Reinforcement Learning course Assignment 3 (see 'Gridworld Problem 2.pdf') at Memorial University of Newfoundland, Aug. 1, 2024

For Gridworld Problem 1, see https://github.com/zyxsjdy/Solve-the-Gridworld-Problem-with-Reinforcement-Learning

Environment

python 3.11.9

Packages: numpy, matplotlib, copy

How to run

Use Jupyter Notebook to open the 'main.ipynb' file, and click Run All to run the file.

'environment.py' is for the gridworld environment.

See explanation for results in 'Report.pdf'.

Included topics

Reinforcement Learning

Gridworld Problem

Part 1:

Sarsa Algorithm

Q-learning Algorithm

Part 2:

Bellman Equation

Gradient Monte Carlo Method

Semi-gradient TD(0) Method

Affine Function Approximation

References

https://marcinbogdanski.github.io/rl-sketchpad

https://github.com/BY571/Medium_Code_Examples