用大模型生成可运行的游戏世界模型，提升预测准确率与目标达成能力。
Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games
- 基于轨迹和截图提取信息，用大模型合成可独立运行的程序化世界模型。
- 在蒙特祖玛复仇者中预测准确率达48.7%，5/8子目标成功验证。
- 适用于需要长程规划的不完全可观测游戏，适合强化学习研究者。
世界模型合成旨在将交互经验转化为对环境动态的内部建模。现有符号方法通常仅拟合观测到的状态转移或局部规则混合，无法生成可脱离真实环境独立运行的完整可执行程序。我们提出Mind-Studio框架，利用大语言模型从状态-动作-下一状态轨迹中合成类似Pygame的可执行世界模型。该框架结合熵选择的轨迹与轻量级游戏技能文件（包含对象、动作和静态场景信息，由截图提取）。通过K步前瞻保真度协议评估合成质量，将生成的世界模型回放与来自Real-ALE的真实回放进行对比。在蒙特祖玛复仇者中，所提方法将选定动作的下一状态预测准确率从PoE-World的0.3%提升至48.7%，并验证了8个子目标中的5个；在Alien、Assault和Skiing中，其分支级保真度优于先前学习的前瞻源。
原文摘要 · Abstract (English)
World-model synthesis aims to turn interaction experience into an internal model of environment dynamics. Existing symbolic approaches often fit observed transitions or mixtures of local rules, but they do not produce a complete executable program that can run independently of the real environment. We present Mind-Studio, a framework that synthesizes executable pygame-style world models from state-action-next-state trajectories using large language models. Mind-Studio combines entropy-selected traces with a lightweight game skill file containing object, action, and static scene information extracted from screenshots. We evaluate synthesis quality with a K-step lookahead fidelity protocol that compares generated world-model rollouts against Real-ALE rollouts from the same state. On Montezuma's Revenge, Mind-Studio improves chosen-action next-state prediction from 0.3% for PoE-World to 48.7% while verifying 5 of 8 subgoals; across Alien, Assault, and Skiing, it achieves stronger branch-level fidelity than prior learned lookahead sources.
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。