Robuta

https://deepai.org/publication/provably-correct-optimization-and-exploration-with-non-linear-policies Provably Correct Optimization and Exploration with Non-linear Policies | DeepAI Mar 22, 2021 - 03/22/21 - Policy optimization methods remain a powerful workhorse in empirical Reinforcement Learning (RL), with a focus on neural policies ... provably correctnon linearoptimizationexplorationpolicies https://www.mail-archive.com/sc-l@securecoding.org/msg01278.html [SC-L] Cost of provably-correct code (was: bumper sticker slogan for secure software)