למידת גבולות לא ידועים ללא נתונים לא בטוחים באמצעות רגולריזציה של אופטימליות וקונטרפקטואלי

תקציר מקורי באנגליתarXiv:2610.09350v1 Announce Type: cross Abstract: Learning from demonstrations (LfD) provides a framework for inferring unknown constraints from locally optimal, constraint-satisfying expert behavior. Existing approaches largely fall into two paradigms, constrained inverse optimal control (CIOC) and inverse constrained reinforcement learning (ICRL). CIOC exploits optimality conditions such as the Karush--Kuhn--Tucker (KKT) conditions but typically assumes known dynamics and structured constraint representations. Meanwhile, ICRL accommodates complex unknown constraints and unknown transition dynamics but often requires extensive online exploration, during which unsafe constraint violations may occur. In this work, we introduce Counterfactual KKT (CF-KKT), a constraint learning framework tha