Titlebook: Automated Technology for Verification and Analysis; 20th International S Ahmed Bouajjani,Luká? Holík,Zhilin Wu Conference proceedings 2022

流逝

挑剔為人

Excitotoxin

Dynamic Shielding for?Reinforcement Learning in?Black-Box Environmentsve been various proposals to reduce undesired behaviors during learning, most of these techniques require prior system knowledge, and their applicability is limited. This paper aims to reduce undesired behaviors during learning without requiring . prior system knowledge. We propose .: an extension o