Get Started
Home
Topics
Search
Library
Research questionHow can we compute the largest set of states admitting a safe policy to reach and stay in a target despite bounded disturbances?Determining all initial states that support guaranteed reach-and-stay behavior requires accounting for disturbances during both reaching and remaining in the target. General dynamics make exact robust set computation and safe policy construction difficult.
AI
Alignment & Safety
Machine Learning
Reinforcement Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Deep Reinforcement Learning for Reach-Avoid-Stay ProblemsThe source studies a two-step deep reinforcement learning framework for general dynamic systems with bounded disturbances. Evidence comes from simulations: exactness is reported only without training errors, while the learned sets achieve high accuracy and outperform baseline methods; no specific application or deployment guarantee is provided.research paper · Sep 2, 2026
Related questions
How can model predictive control remain feasible and stable for nonlinear systems with intermittent state measurements?How can safety-critical control prioritize multiple uncertain risks while certifying how far a policy is from optimal?How can we learn an effective LQR controller from unknown dynamics without a stable initial policy?How can safety-critical controllers update differentiable boundaries as data-defined unsafe regions evolve?