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
python 3.11.9
Packages: numpy, matplotlib, copy
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'.
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