📗 In this competition, you will implement the minimax algorithm with some static board evaluation function to play the Connect Four game: Wikipedia. The first player has a winning strategy, but it is difficult to compute the best responses in real time. Instead, you will use some heuristic with a depth limit to solve for approximate best responses.
📗 Submit a policy neural network to play against other students.
📗 You will play twice with each of the other players in your team and your score will be the number of wins plus \(0.5\) times the number of ties.
📗 You can play against a simple minimax (with depth limit) player with a simple SBE heuristic.
You are player , and start with the following state:
Your submission should contain (i) your player name (not necessarily your real name), (ii) your player icon (single emoji from this list: Link), (iv) your network weights if you are the first player, (v) [optional] your second network weights if you are the second player (if not provided, the same network will be used).