Overview: This project involves developing AI agents to play a simplified version of the Go game, known as Little-Go, with a 5x5 board. The objective is to implement and train AI agents using various techniques such as Search, Game Playing, and Reinforcement Learning to compete in online tournaments.

Players: Two players, Black and White.

Board: A 5x5 grid where players place stones at intersections.

Objective: Surround more territory than the opponent by strategically placing stones.

Rules: Includes Liberty (No-Suicide) and KO rules to determine valid moves and captures.

Search Algorithms: Implement Minimax with Alpha-Beta Pruning to evaluate possible moves and choose the best one.

Reinforcement Learning: Use Q-Learning to train the agent through simulated games, learning optimal strategies over time.

Initialization: Set up the initial game state and parameters.

Move Generation: Create functions to generate valid moves based on current board state.

Evaluation Function: Develop a function to evaluate board states and determine the best moves.

Training: Train the AI agents using simulated games to improve their decision-making abilities.

Performance Metrics: Evaluate the agent's performance based on win rate and score against various AI opponents.

Competitions: Participate in staged competitions against predefined AI agents such as Random, Greedy, Aggressive, Alpha-Beta, Q-Learning, and Championship players.