Conjecture—Compositional representations required for specifying models and tasks

Establish the necessity of compositional representation frameworks for specifying embodied agents’ world models and tasks, enabling generalization and rapid adaptation to novel environments.

Background

Logical and compositional representations can support systematic generalization and compact specification of large problems.

The authors conjecture that representations with specific forms of compositionality are required to effectively specify both models and tasks for embodied agents.

References

We conjecture that a specific form of compositionality is required of the representation that is absent from many architectures, and we address this conjecture in section \ref{sec:logic}.

— From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence  (2110.15245 - Roy et al., 2021) in Section 1 (Introduction: Guiding Questions)