AI 中文总结
该研究针对多智能体系统中世界模型因相关性与因果机制混淆导致分布偏移下失效的问题，提出隐式因果世界模型，经评估在协调任务上表现出可解释因果表示且精度随干预强度提升。
AI 中文摘要
在基于模型的强化学习中，世界模型作为内部模拟器存在，但其训练常将统计相关性与因果机制混淆。多智能体系统中该问题更严重，因物理转移与智能体策略意图交织，导致世界模型在分布偏移下失效。我们提出隐式因果世界模型，无需预定义因果图即可从离线演示中恢复环境动态，通过纳入策略方差，使世界模型可通过序列后门条件被发现。在协调任务（Two-Door、Navigation、Giveway）上的评估表明，这些模型在全观测与部分观测下均提供可解释的因果表示，模型精度与干预强度直接相关。
英文摘要
In model-based reinforcement learning, world models exist as internal simulators, but their training often conflates statistical correlations with causal mechanisms. This problem is exacerbated in multi-agent systems where physical transitions are intertwined with strategic agent intents, causing world models to fail under distribution shift. We introduce Implicit Causal World Models to recover environmental dynamics from offline demonstrations without requiring pre-defined causal graphs. By incorporating policy variance, we render world models discoverable via the sequential backdoor condition. Evaluations across coordination tasks (Two-Door, Navigation, and Giveway) demonstrate that these models provide interpretable causal representations under both full and partial observability, with model accuracy scaling directly with interventional strength.
CommentsPreprint
