Provided are certified adversarial robustness for deep reinforcement learning. The present disclosure describes systems and methods that include calculating one or more lower bound state-action values based on a corrupted observation and a predetermined perturbation parameter; and selecting an action corresponding to a lower bound state-action value having the highest value.
本发明提供了“用于深度强化学习的认证对抗鲁棒性”。本公开描述了系统和方法,所述系统和方法包括:基于损坏的观察值和预定扰动参数来计算一个或多个下界状态‑动作值;以及选择对应于具有最高值的下界状态‑动作值的动作。
CERTIFIED ADVERSARIAL ROBUSTNESS FOR DEEP REINFORCEMENT LEARNING
用于深度强化学习的认证对抗鲁棒性
2021-04-23
Patent
Electronic Resource
Chinese
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / H04W WIRELESS COMMUNICATION NETWORKS , Drahtlose Kommunikationsnetze |
British Library Conference Proceedings | 2018
|Environment Adversarial Reinforcement Learning
AIAA | 2024
|