← Search

I-Te Danny Hung

2 accepted papers

2022

Training a Resilient Q-network against Observational Interference

AAAI 2022technical

Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive faulty observation by abrupt interferences such as black-out, frozen-screen, and adversarial perturbation. How to design…

2020

Enhanced Adversarial Strategically-Timed Attacks Against Deep Reinforcement Learning

ICASSP 2020accepted

Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e.g., autonomous navigation and continuous robot arm c…

Cited by 0SourceScholar