39 citations · 48 across the 2 of their papers we have counts for
3 papers
cs.RO2022★ 39 cited
Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Niklas Kochdumper, Hanna Krasowski, Xiao Wang +2
While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critica…
cs.LG2022★ 9 cited
Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking
Hanna Krasowski, Jakob Thumm, Marlon Müller +3
Ensuring the safety of reinforcement learning (RL) algorithms is crucial to unlock their potential for many real-world tasks. However, vanilla RL and most safe RL approaches do not…
cs.RO2020
Falsification-Based Robust Adversarial Reinforcement Learning
Xiao Wang, Saasha Nair, Matthias Althoff
Reinforcement learning (RL) has achieved enormous progress in solving various sequential decision-making problems, such as control tasks in robotics. Since policies are overfitted…