Reinforcement Learning for ConnectX
Artificial Intelligence
2022-10-18 v1
Abstract
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.
Cite
@article{arxiv.2210.08263,
title = {Reinforcement Learning for ConnectX},
author = {Sheel Shah and Shubham Gupta},
journal= {arXiv preprint arXiv:2210.08263},
year = {2022}
}