A self learning AI Tic-Tac-Toe bot, that after training performs perfectly. Uses a custom implementation of a Value-based reinforcement learning model, with a greedy policy that nevertheless forces exploration due to the way it is defined.
AI self learning
A self learning AI Tic-Tac-Toe bot, that after training performs perfectly. Uses a custom implementation of a Value-based reinforcement learning model, with a greedy policy that nevertheless forces exploration due to the way it is defined.
AI self learning