Learning Implicit Causal World Models from Multi-Agent Demonstrations
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Maximum Causal Entropy Inverse Constrained Reinforcement Learning
When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, …
reinforcement-learningReinforcement LearningBeyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols eithe…
CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations
Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results wh…
Formreinforcement-learningReinforcement Learning (RL)RetrievalDemo-JEPA: Joint-Embedding Predictive Architecture for One-shot Cross-Embodiment Imitation
Robotic imitation learning is often treated as reproducing demonstrated actions, but actions are inherently embodiment-specific. When demonstrations come from humans or robots with different morphology, kinematics, or ac…
Reinforcement Learning via Reasoning from Demonstration
Demonstration is an appealing way for humans to provide assistance to reinforcement-learning agents. Most approaches in this area view demonstrations primarily as sources of behavioral bias. But in sparse-reward tasks, h…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)