Causal Imitability Under Context-Specific Independence Relations
This work addresses causal imitation learning for AI/robotics by incorporating overlooked CSI information, though it is incremental as it builds on existing causal methods.
The paper tackles the problem of causal imitation learning when context-specific independence (CSI) relations are known, proving that the feasibility decision problem is NP-hard and providing a necessary graphical criterion, which is sufficient under a structural assumption, along with a sound algorithmic approach.
Drawbacks of ignoring the causal mechanisms when performing imitation learning have recently been acknowledged. Several approaches both to assess the feasibility of imitation and to circumvent causal confounding and causal misspecifications have been proposed in the literature. However, the potential benefits of the incorporation of additional information about the underlying causal structure are left unexplored. An example of such overlooked information is context-specific independence (CSI), i.e., independence that holds only in certain contexts. We consider the problem of causal imitation learning when CSI relations are known. We prove that the decision problem pertaining to the feasibility of imitation in this setting is NP-hard. Further, we provide a necessary graphical criterion for imitation learning under CSI and show that under a structural assumption, this criterion is also sufficient. Finally, we propose a sound algorithmic approach for causal imitation learning which takes both CSI relations and data into account.