LATIDIA · Robótica

Control neuronal autoconsistente: trayectorias de aprendizaje para el equilibrio implícito

arXiv:2611.03885v1 Anuncio Tipo: nuevo Resumen: Un gran desafío en la IA física es interactuar con sistemas cuyos estados están definidos por el equilibrio implícito. El aprendizaje en estos sistemas es difícil debido a su respuesta

La noticia

arXiv:2611.03885v1 Announce Type: new Abstract: One big challenge in physical AI is interacting with systems whose states are defined by implicit equilibrium. Learning in these systems is difficult because their responses can be multistable, path-dependent, and sensitive over long horizons. Adjoint learning provides an efficient way to optimize trajectories without unrolling iterative equilibrium solvers, but its gradient relies on the frozen-tangent approximation, which neglects higher-order sensitivity terms and can become inaccurate when the local equilibrium varies rapidly. In this work, we introduce Self-Consistent Neural Control (SCNC), optimizing trajectories along which sensitivity variations are explicitly controlled. We derive a mathematical bound on the resulting gradient error and develop a practical finite-difference