Log In Sign Up

The Go Transformer: Natural Language Modeling for Game Play

by   Matthew Ciolino, et al.

This work applies natural language modeling to generate plausible strategic moves in the ancient game of Go. We train the Generative Pretrained Transformer (GPT-2) to mimic the style of Go champions as archived in Smart Game Format (SGF), which offers a text description of move sequences. The trained model further generates valid but previously unseen strategies for Go. Because GPT-2 preserves punctuation and spacing, the raw output of the text generator provides inputs to game visualization and creative patterns, such as the Sabaki project's (2020) game engine using auto-replays. Results demonstrate that language modeling can capture both the sequencing format of championship Go games and their strategic formations. Compared to random game boards, the GPT-2 fine-tuning shows efficient opening move sequences favoring corner play over less advantageous center and side play. Game generation as a language modeling task offers novel approaches to more than 40 other board games where historical text annotation provides training data (e.g., Amazons Connect 4/6).


page 1

page 2

page 3

page 5

page 6


The Chess Transformer: Mastering Play using Generative Language Models

This work demonstrates that natural language transformers can support mo...

Learning Chess Blindfolded: Evaluating Language Models on State Tracking

Transformer language models have made tremendous strides in natural lang...

Human Language Modeling

Natural language is generated by people, yet traditional language modeli...

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

The application of Generative Pre-trained Transformer (GPT-2) to learn t...

Learning from flowsheets: A generative transformer model for autocompletion of flowsheets

We propose a novel method enabling autocompletion of chemical flowsheets...

Word Play for Playing Othello (Reverses)

Language models like OpenAI's Generative Pre-Trained Transformers (GPT-2...

Predicting Strategic Behavior from Free Text

The connection between messaging and action is fundamental both to web a...