AI and Computational Intelligence

Welcome to the AI and Computational Intelligence repository. This repository is a comprehensive collection of Problem-Based Learning (PBL) projects, each delving into different realms of artificial intelligence. Covering a range of topics from fuzzy logic and the Knight's Tour problem to the Game of Nim and reinforcement learning challenges, these projects blend practical applications with theoretical insights in AI and computational intelligence.

Projects Overview

PBL 1. Fuzzy Logic

• Topic: Fuzzy Logic Automatic Braking Controller
• Description: Implementation of an intelligent Automatic Braking System using Fuzzy Logic.
• Key Features: Interactive implementation, comprehensive explanations, and simulation of real-world scenarios.
• Read More

PBL 2. Knight's Tour

• Topic: Solving the Knight's Tour Problem
• Description: A Python program to solve the Knight's Tour problem on an n x n chessboard using an efficient backtracking algorithm.
• Key Features: Interactive GUI, algorithm analysis, and performance metrics.
• Read More

PBL 3. Game of Nim

• Topic: The Game of Nim
• Description: Players compete against a computer AI in the classic strategy game of Nim.
• Key Features: AI opponent using the Minimax algorithm, configurable game settings, and strategic gameplay.
• Read More

Final Project: Reinforcement Learning Investigation

• Description: A series of projects exploring reinforcement learning challenges such as the Cartpole, Mountain Car, and Taxi Problem.
• Key Topics: Application of reinforcement learning techniques, performance analysis, and algorithmic comparison.
• Read More

Getting Started

To explore each project:

1. Clone this repository:

   git clone https://github.com/GeorgeNich/AI-and-Computational-Intelligence.git

2. Navigate to the individual project directories.
3. Follow the instructions in the respective README.md files for setup and running the projects.

Prerequisites

• Python 3.x
• Relevant Python libraries as specified in each project's requirements (e.g., numpy, matplotlib, gym, tkinter).

Acknowledgments

This project has been greatly enriched and influenced by a variety of sources in the field of Reinforcement Learning. Special thanks to the following authors and their valuable contributions:

• Brendan Martin, S. K., and others
• Fakhry, A., and others
• Frans, K., and others
• Hayes, G., and others
• Ihvy, L., and others

Their insights and information have been instrumental in the development and understanding of the strategies and algorithms implemented in this project.

License

This project is licensed under the MIT License - see the LICENSE file for details.