BURNS computes sound underapproximate backward reachable sets for discrete-time nonlinear neural feedback loops using mixed-integer linear programming, enabling goal-reaching verification.
Scal- able multi-robot cooperation for multi-goal tasks using reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BURNS: Backward Underapproximate Reachability for Neural-Feedback-Loop Systems
BURNS computes sound underapproximate backward reachable sets for discrete-time nonlinear neural feedback loops using mixed-integer linear programming, enabling goal-reaching verification.