从游戏视频中提取有限自动机，让世界模型变成可读程序
Finite Automata Extraction: Low-data World Model Learning as Programs from Gameplay Video
- 用新领域语言将游戏视频转为可执行代码
- 在低数据下仍能精准捕捉环境动态变化规律
- 适合需要可解释性的强化学习与游戏逆向工程
世界模型是环境的空间与时间特征的压缩表示，通常由神经网络实现，导致其动态迁移困难且难以解释。本文提出有限自动机提取（FAE）方法，从游戏视频中学习一种神经符号化世界模型，以新颖领域专用语言（Retro Coder）表示为程序。相比以往世界模型方法，FAE 在低数据条件下仍能学习更精确的环境模型和更具泛化的代码表达，优于先前基于DSL的方法。
原文摘要 · Abstract (English)
World models are defined as a compressed spatial and temporal learned representation of an environment. The learned representation is typically a neural network, making transfer of the learned environment dynamics and explainability a challenge. In this paper, we propose an approach, Finite Automata Extraction (FAE), that learns a neuro-symbolic world model from gameplay video represented as programs in a novel domain-specific language (DSL): Retro Coder. Compared to prior world model approaches, FAE learns a more precise model of the environment and more general code than prior DSL-based approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。