This is a project template from UC Berkeley. The project implements Value Iteration and Q-Learning algorithms to solve a variety of gridworld mazes and puzzles. It provides pre-defined policies that can be customized by adjusting parameters like discount, noise, and reward values, as well as policy optimization through iterative reinforcement learning. Additionally, it utilizes Epsilon Greedy values in Q-value iteration to introduce exploration capabilities to the agent, which enhances policy improvement and maze-solving time.
-
: To be filled
-
: To be filled
Follow these steps to set up and run the Gridworld Reinforcement Learning project:
-
Download or clone the repository to your local machine:
git clone https://github.com/Daksh2060/gridworld-reinforcement-learning
Feel free to reach out if you have any questions, suggestions, or feedback:
- Email: dpa45@sfu.ca
- LinkedIn: @Daksh Patel