Compiling VGDL into Causal Models

将 VGDL 编译为因果模型

Abstract: Reinforcement learning and large language models often struggle to accurately capture the causal mechanics of game environments. Standard reinforcement learning agents tend to rely on spurious correlations, while large language models are prone to hallucinating game rules. Although causal reinforcement learning improves interpretability, there is currently no formal methodology to map complex game mechanics directly into causal models.

摘要： 强化学习和大语言模型往往难以准确捕捉游戏环境中的因果机制。标准的强化学习智能体倾向于依赖虚假相关性，而大语言模型则容易产生游戏规则的幻觉。尽管因果强化学习提高了可解释性，但目前尚无将复杂游戏机制直接映射为因果模型的正式方法。

To address this, we propose a deterministic framework that compiles games specified in the Video Game Description Language into Dynamic Structural Causal Models. Rather than inferring causal structures from gameplay traces or noisy large language models’ outputs, our methodology directly translates game components, including sprite dynamics, interaction rules, and termination conditions, into explicit structural equations.

为了解决这一问题，我们提出了一种确定性框架，将使用视频游戏描述语言（VGDL）定义的游戏编译为动态结构因果模型。我们的方法并非从游戏轨迹或嘈杂的大语言模型输出中推断因果结构，而是直接将游戏组件（包括精灵动态、交互规则和终止条件）转换为明确的结构方程。

Each game tick represents a causal transition from state variables at time $t$ to $t+1$. By establishing this grounded mapping, the approach guarantees absolute causal fidelity to the ground-truth game mechanics. The resulting models offer transparent causal pathways that support counterfactual reasoning, causal reinforcement learning agent training, and procedural content validation. This framework provides a principled bridge between symbolic game descriptions and causally grounded game AI.

每一个游戏时钟周期都代表了从时间 $t$ 到 $t+1$ 状态变量的因果转换。通过建立这种扎实的映射，该方法保证了对真实游戏机制的绝对因果保真度。由此产生的模型提供了透明的因果路径，支持反事实推理、因果强化学习智能体训练以及程序化内容验证。该框架为符号化游戏描述与基于因果的游戏人工智能之间架起了一座原则性的桥梁。