Tootfinder

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Raphael Simon, Pieter Libin, Wim Mees
https://arxiv.org/abs/2509.20008 https://…

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investi…