Human-Feedback Shield Synthesis for Perceived Safety in Deep Reinforcement Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2021.3128237
Abstract: Despite the successes of deep reinforcement learning (RL), it is still challenging to obtain safe policies. Formal verification approaches ensure safety at all times, but usually overly restrict the agent’s behaviors, since they assume adversarial… read more here.
Keywords: shield synthesis; safety; reinforcement learning; deep reinforcement ... See more keywords