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

2021-09-07 · David Noever, Ryerson Burdick

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 ($>10^{19}$) for the games provides a puzzle environment in which the solution has few intermediate rewards and a final move that solves the challenge.

📄 PDF Abstract BibTeX arXiv:2109.02797

Code (0)

등록된 구현이 없습니다.

Tasks

Rubik's Cube

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Multi-Head Attention 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning

2024-03-06 · Deepanway Ghosal, Vernon Toh Yan Han, Chia Yew Ken, Soujanya Poria

This paper introduces the novel task of multimodal puzzle solving, framed within the context of visual question-answering. We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of mu…

Multimodal Reasoning Question Answering Visual Question Answering

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

Code (0)

Tasks

Methods 이 논문이 사용한 방법론

Similar Papers 제목 키워드 기반

Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning

Can LLMs Generate and Solve Linguistic Olympiad Puzzles?

Solving Witness-type Triangle Puzzles Faster with an Automatically Learned Human-Explainable Predicate

Solving Pictorial Jigsaw Puzzle by Stigmergy-inspired Internet-based Human Collective Intelligence

From Square Pieces to Brick Walls: The Next Challenge in Solving Jigsaw Puzzles