This project is a solution for the UC Berkeley Pacman AI course project, incorporating additional code and solutions. The project covers various topics in artificial intelligence, including Uninformed and Informed Search, Game Search, Constraint Satisfaction Problem (CSP), Probabilistic Inference using Bayesian Networks, and Reinforcement Learning.
This project provides a comprehensive solution for the UC Berkeley Pacman AI course project. It builds upon the existing codebase provided by the course, incorporating additional code and solutions to complete the various assignments, beyond the Pacman project as well.
The project covers several fundamental concepts in artificial intelligence, allowing exploration and implementation of algorithms related to Uninformed and Informed Search, Game Search, Constraint Satisfaction Problem (CSP), Probabilistic Inference using Bayesian Networks, and Reinforcement Learning.
search/- Contains code related to search algorithms, including uninformed and informed search.multiagent/- Contains code for multi-agent search algorithms, which are used in the game-playing scenarios.reinforcement/- Contains code that implements reinforcement learning algorithms to train Pacman agents, allowing them to learn and improve their behavior through interaction with the environment.tracking/- Contains code dealing with probabilistic inference in a hidden Markov model tracks the movement of hidden ghosts in the Pacman world.csp/- Separate from the Pacman game, this contains code for dealing with Constraint Satisfaction Problems (CSPs) like Kakuro.
To get started with the project, follow these steps:
- Clone the repository:
git clone https://github.com/aravindsomaraj/aiproject-pacman.git - Python3 is required. No other dependencies required.
python3 --version # if not installed sudo apt-get install python3
- Navigate to the project directory:
Specific instructions for each sub-directory is mentioned further in.
cd aiproject-pacman