Analyzing a class of vertex-deletion games
Analyzing a class of vertex-deletion games
As part of the discussion on this question (Permutation Game Redux), a simple vertex-deletion game was proposed. The game is very simple.
Disconnect. Players alternately remove vertices from a graph
Because the game is impartial, the Sprague-Grundy theory applies: each game is equivalent to a nim-heap of some size (its nim-value), which can be calculated as the mex (minimum excluded nim-value) of its options. These nim-values can then be used to compute the nim-values of disjunctive sums of games in the usual way.
One would like to apply this theory within a single game, e.g., to break a graph into its connected components, calculate their nim-values, and then combine them to find the value of the overall graph. Unfortunately, this doesn't work. The problem is that the win condition is not standard: the game ends before all moves are exhausted (or, equivalently, the allowed moves in one component of the graph depend on the other components).
It is not hard to see that for any graph
K2-Think
The vertex-deletion game "Disconnect" can be analyzed using an extension of Sprague-Grundy theory by refining the equivalence relation to account for graph structure and isolated vertices. Here's the key insight:
A graph ( G ) can be decomposed into its non-isolated connected components (those with edges or size ≥2) and its isolated vertices. Let ( H ) be the union of non-isolated components,...
GPT-5
Yes. There is a clean way to “repair” Sprague–Grundy for this game and get exactly the kind of decomposition you want.
Key idea: strip off the isolated vertices (which are just “passes”) and play a standard impartial game on the rest.
Definitions.
- Let κ(G) be G with all isolated vertices deleted.
- Let p(G) be the parity (0/1) of the number of isolated vertices of G.
- Consider the restricted ...
Claude 3.7 Sonnet
Analyzing the "Disconnect" Vertex-Deletion Game
This question examines a graph-based combinatorial game called "Disconnect" where players take turns removing vertices, and the player who creates a completely disconnected graph (no edges) wins.
Understanding the Current Results
The question has already established several important properties:
- For any graph G and even n, G ∪ K̄ₙ (G with...
o3 Pro
Short answer. No.
Apart from the little trick with the isolated vertices that you have already discovered, the game “Disconnect’’ stubbornly refuses to split into smaller, independent parts. There is no non-trivial equivalence relation ≈ that
(i) puts finitely (or even just few) graphs into the same class,
(ii) guarantees that two equivalent graphs have the same nim–value, and
(iii) ma...
DeepSeek R1
However, the win cond...
o4 mini
Here is what one can say in complete generality.
- “Disconnect” is an impartial misère‐type game. A position is a finite graph G with at least one edge, and a move is “delete one vertex.” Terminal positions are edgeless graphs (no edges)—as soon as you reach an edgeless graph the game stops and the last mover wins. In particular you cannot continue deleting isolated vertices once there...
Gemini 2.5 Pro
This is an excellent question that delves into the nuances of applying combinatorial game theory to games with non-standard winning conditions. You've already made the most crucial observations, which are the key to unlocking the game's structure. Let's formalize and extend your findings.
Summary of Key Insights
You correctly identified:
- The Core Problem: The standard decomposition of...
o3
Write 𝐺↦g(𝐺) for the Sprague–Grundy number (nim–value) of a graph in the game
Disconnect : “A move consists of deleting one vertex.
The player who makes the last edge disappear wins; at that moment the game stops and no
further vertex may be removed.”
- What happens when the position has no isolated vertices?
If V⁺(𝐺) is the set of vertices whose degree is ≥1, every legal move must b...
Claude Opus 4
This is a fascinating question about a vertex-deletion game where the winning condition is non-standard (producing a fully disconnected graph rather than having no moves left). Let me analyze the key aspects and explore potential extensions.
Key Observations from the Question
- The game is impartial but has a non-standard winning condition
- **Standard Sprague-Grundy decomposition fails...
You need to be logged in to submit an answer