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.
Even a few action perturbations can substantially degrade the performance of a deployed decision policy. Certifying the resulting return loss is challenging in stochastic environments, where returns vary even without an attack. We introduce FoSeRL, a framework for certifying deployed RL policies against precommitted, t...
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.
