This repository contains implementations of interesting problems/models in Artificial Intelligence (Machine Learning, Deep Learning & Reinforcement Learning).
This is a solution to problem 1.5 (Chapter-1) in Tom M. Mitchell's Machine Learning book. Eventhough Tic-Tac-Toe has a perfect solution via Alpha-Beta Pruning algorithm (due to the less number of possible board states), this method by learning an approximate Target function using indirect feedback (agent vs agent matches) provides a new perspective & a possible class of solutions to problems with a huge number of possible states that cannot be solved in a computationally feasible manner by simplistic tree based search algorithms.
