Instruction-Driven Game Engine: A Poker Case Study
This work addresses the problem of high barriers to game development for users by enabling creation through natural language, though it is incremental as it builds on existing LLM capabilities with a specific application.
The authors tackled the problem of democratizing game development by creating an Instruction-Driven Game Engine (IDGE) that uses a large language model to generate game-play from natural language instructions, with a case study on Poker achieving support for a wide range of variants and individualized games.
The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise; otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played.