Instruction-Driven Game Engine: A Poker Case Study
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 17 Oct 2024.
Builds on
27 of 42 references.
References · 27
- 2017Attention Is All You Needcited by 59,932
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
- 2023Baichuan 2: Open Large-scale Language Modelscited by 664
- 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
- 2023Tool Learning with Foundation Modelscited by 302
15 more
- 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
- 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
- 2020The NetHack Learning Environmentcited by 196
- 2024Large Language Models and Games: A Survey and Roadmapcited by 91
- 2024Scaling Instructable Agents Across Many Simulated Worldscited by 67
- 2024From Role-Play to Drama-Interaction: An LLM Solutioncited by 42
- 2024With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generationcited by 36
- 2024IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generationcited by 35
- 2022Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learningcited by 27
- 2023Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysiscited by 20
- 2023Toward Adversarial Training on Contextualized Language Representationcited by 10
- 2023Empower Nested Boolean Logic via Self-Supervised Curriculum Learningcited by 7
- 2023PokerKit: A Comprehensive Python Library for Fine-Grained Multi-Variant Poker Game Simulationscited by 3
- 2023Complexity-Guided Curriculum Learning for Text Graphscited by 3
- 2024Open Role-Playing with Delta-Enginescited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.