Paper proposes CGWMs, learning interpretable world model concept representations with temporal logic
Neurosymbolic Learning of Interpretable World Models
The paper proposes Concept-Grounded World Models (CGWMs), which learn interpretable concept representations from observations using complete knowledge expressed in temporal logic rather than black-box representations. Planning is formulated as differentiable inference, optimizing agent actions via gradient ascent to satisfy goals. In comparisons with pure-neural and neurosymbolic baselines in two game environments, CGWMs' concept grounding is more accurate, holds over long horizons as well, and plans more robustly both in and out of distribution.
The paper places temporal-logic knowledge in the same framework as concept learning and planning for world models, and compares against pure-neural and neurosymbolic baselines in two game environments, making it a basis for judging the method trade-offs of this line of work.
Source: arXiv Game World Models & Generation · arxiv.org