Reinforcement Learning for ConnectX
This work addresses a novel game challenge for AI researchers, but it appears incremental as it applies existing methods without clear breakthroughs.
The paper tackled the problem of playing ConnectX, a generalized version of Connect 4 with variable board sizes and win conditions, by implementing and modifying reinforcement learning algorithms, but no concrete results or numbers were reported.
ConnectX is a two-player game that generalizes the popular game Connect 4. The objective is to get X coins across a row, column, or diagonal of an M x N board. The first player to do so wins the game. The parameters (M, N, X) are allowed to change in each game, making ConnectX a novel and challenging problem. In this paper, we present our work on the implementation and modification of various reinforcement learning algorithms to play ConnectX.