Undirected edge geography games on grids
Tharit Sereekiatdilok, Panupong Vichitkunakorn
TL;DR
This work completely characterizes the rooted Undirected Edge Geography on grid graphs $G_{m\times n}$ by showing that, with $d=\gcd(m+1,n+1)$, the position $(G_{m\times n},v)$ is a P-position precisely when $d \nmid a$ and $d \nmid b$, generalizing the corner result. The main method combines geometric trails (a 90-degree trail for N-positions and a 180-degree trail for P-positions) with region-labeling and the construction of even kernels; explicit $S_k$ families provide concrete kernel realizations. The results yield complete winning strategies: a closed $90$-degree trail leads to a winning move for the next player, while a $180$-degree trail yields a P-position via an even kernel. Overall, the paper advances understanding of geography-type games on grids by delivering exact classifications and constructive strategies for all rooted positions.
Abstract
The undirected edge geography is a two-player combinatorial game on an undirected rooted graph. The players alternatively perform a move consisting of choosing an edge incident to the root vertex, removing the chosen edge, and marking the other endpoint as a new root vertex. The first player who cannot perform a move is the loser. In this paper, we are interested in the undirected edge geography game on the grid graph $P_m\square P_n$. We completely determine whether the root vertex is a winning position (N-position) or a losing position (P-position). Moreover, we give a winning strategy for the winner.
