Introduces a Lipschitz continuous reach-avoid value function whose zero sublevel set characterizes the reach-avoid set exactly and combines it with robust control Lyapunov-value functions for stabilize-avoid problems.
Bridging hamilton-jacobi safety analysis and reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.
citing papers explorer
-
Solving Reach- and Stabilize-Avoid Problems Using Discounted Reachability
Introduces a Lipschitz continuous reach-avoid value function whose zero sublevel set characterizes the reach-avoid set exactly and combines it with robust control Lyapunov-value functions for stabilize-avoid problems.
-
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
The authors introduce affine repulsive RL policies that provably satisfy hard affine state constraints for black-box hybrid dynamical systems with affine reset maps by deriving sufficient closed-loop safety conditions and testing on pendulum and juggler examples.