In this assignment , you need to build an RLagent that learns to play Numerical Tic-Tac-Toe with odd numbers (the agent will always make the first move). You need to train your agent using Q-Learning...

In this assignment, you need to build an RLagent that learns to play Numerical Tic-Tac-Toe withodd numbers(the agent will always make the first move). You need to train your agent usingQ-Learning. The environment is playing randomlywith the agent, i.e. its strategy is to put an even number randomly in an empty cell. If your agent wins the game, it gets 10 points, if the environment wins, the agent loses 10 points. And if the game ends in a draw, it gets 0. Also, you want the agent to win in as few moves as possible, so for each move, it gets a -1 point.The two starter code files (Environment and Agent) are given