We have 4 of 24 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
FoSeRL, a framework for certifying deployed RL policies against precommitted, temporally sparse action attacks, is introduced, which achieves substantially larger certified budgets than policy smoothing, and reveals marked robustness differences among policies with comparable nominal performance.
This work constructs a smaller decision tree, distilling the essence of the controller, while still guaranteeing its $\varepsilon$-optimality, which enables the tool to provide tunably simpler explanations, omitting a controllable amount of detail.
RATTL targets runtime safety for agents, including LLM-based systems, acting under uncertainty, and proves a Safety Sandwich: the RATTL value lies between the uninformed robust value and the full- knowledge optimum, with a gap that vanishes as the posterior concentrates.
An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity---a confidence level fixes the radius of a relative-entropy ball of alternative models---but that ball cannot reach catastrophes the nominal...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
