A reformulation of joint chance constrained optimal control that minimizes expected cost solely over safe trajectories, solved via constrained MDP and dynamic programming with derived safety bounds under state-space gridding.
Trustworthy reinforcement learning against intrinsic vulnerabilities: Robustness, safety, and generalizability
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.
citing papers explorer
-
Joint Chance Constrained Safe-Optimal Control
A reformulation of joint chance constrained optimal control that minimizes expected cost solely over safe trajectories, solved via constrained MDP and dynamic programming with derived safety bounds under state-space gridding.
-
Why Does Agentic Safety Fail to Generalize Across Tasks?
Agentic safety fails to generalize across tasks because the task-to-safe-controller mapping has a higher Lipschitz constant than the task-to-controller mapping alone, as proven in linear-quadratic control and demonstrated in quadcopter and LLM experiments.