Infinite Energy puzzles show varied difficulty from simple to complex

Hardness of "Infinite Energy" Puzzles

Computational Complexity

Summary

Infinite Energy is a puzzle game where you connect sockets so energy circulates endlessly after unplugging power sources. The paper studies how hard it is to solve different versions of this game. Some versions are very hard to decide (in computer science terms, NP-hard), while simpler versions can be solved efficiently by computers. The authors also found tricky cases where common strategies fail and identified open questions about certain game variations.

What this means in practice

  • For game designers: Design puzzle games with known complexity levels by understanding which Infinite Energy variants are solvable or hard.
  • For algorithm engineers: Use complexity classifications from Infinite Energy variants to anticipate difficulty in network flow or circuit simulation problems.

A theory result. No direct application yet.

Authors

Utkarsh Tiwari, Utkarsh Thanvi, Armaan Sethi, Aalok Thakkar, Neeldhara Misra

Abstract

Infinite Energy (by Light Potato, 2025) is a single-player puzzle in which one wires a network of sockets so that, after every power source is unplugged, energy keeps circulating and leaves every board energized. We study several variants of the game and the complexity of deciding whether an instance can be won. The variants can be played at https://infinite-energy-peer-review.netlify.app, which also has worked examples of the reduction techniques. The colorless game, with connectability given by an arbitrary matrix, is NP-hard (by reduction from Hamiltonian Path) and lies in PSPACE. We give a seven-socket instance winnable only by charging a temporary battery loop and then breaking it, so the natural "charge and keep" strategy fails. We reduce NP-membership to one conjecture: that every winnable instance has a winning play in which no socket is charged twice. Two variants bound the complexity more tightly. The unconstrained variant, in which connectability is unrestricted, is $\mathsf{TC}^0$-complete under $\mathsf{AC}^0$ Turing reductions (hence in L). The geometric variant, in which connectability is set by proximity of points in $\mathbb{R}^k$, stays NP-hard for every fixed $k \ge 2$ via reduction from Hamiltonian Path over grid graphs. The one-dimensional case is open. The colored variant is NP-hard, though a matching upper bound remains open.