Showing 2026 · cs.AIShow all
2 papers · 2 filters
cs.AI2026
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Ezequiel Companeetz, Santiago Cifuentes, Sergio Abriola
We address the problem of explainability in machine learning models through feature attribution methods. In particular, we consider a variant of Shapley values known as Asymmetric…
cs.AI2026
General Agents Contain World Models, even under Partial Observability and Stochasticity
Santiago Cifuentes
Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within…