ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2109.02797
174
7

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

7 September 2021
David Noever
Ryerson Burdick
    ReLM
ArXivPDFHTML
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}>1019) for the games provides a puzzle environment in which the solution has few intermediate rewards and a final move that solves the challenge.

View on arXiv
Comments on this paper