English

Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach

Machine Learning 2021-09-08 v1 Artificial Intelligence Computation and Language

Abstract

The application of Generative Pre-trained Transformer (GPT-2) to learn text-archived game notation provides a model environment for exploring sparse reward gameplay. The transformer architecture proves amenable to training on solved text archives describing mazes, Rubik's Cube, and Sudoku solvers. The method benefits from fine-tuning the transformer architecture to visualize plausible strategies derived outside any guidance from human heuristics or domain expertise. The large search space (>1019>10^{19}) for the games provides a puzzle environment in which the solution has few intermediate rewards and a final move that solves the challenge.

Keywords

Cite

@article{arxiv.2109.02797,
  title  = {Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach},
  author = {David Noever and Ryerson Burdick},
  journal= {arXiv preprint arXiv:2109.02797},
  year   = {2021}
}
R2 v1 2026-06-24T05:44:22.087Z