Learning Implicit Causal World Models from Multi-Agent Demonstrations

Researchers introduced Implicit Causal World Models to recover environmental dynamics from offline multi-agent demonstrations without pre-defined causal graphs, addressing the failure of world models under distribution shift. Evaluations across coordination tasks (Two-Door, Navigation, Giveway) showed interpretable causal representations under full and partial observability, with accuracy scaling with interventional strength.

arXiv:2607.26336v1 Announce Type: new Abstract: 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.