The following project is Q-learning based Implementation of Tic-Tac-Toe program.
Following are descriptions of different Files: 1.Training_Players.py - Here,Player1-Attacker(one who plays first) and defender(who players 2nd) are trainend using Value updation Function. 2)Player1 and Player2-These are the pickle files of the players trained in Training_Players.py 3)Play.py - This file is used to Play with computer .Player1 and Player2 are imported in this files depending upon whether you or computer playes first