Safe Deep Reinforcement Learning by Verifying Task-Level Properties.

Enrico Marchesini Luca Marzari Alessandro Farinelli Christopher Amato

Published in: CoRR (2023)

Keyphrases

reinforcement learning
function approximation
databases
machine learning
temporal difference
multiscale
model checking
reinforcement learning algorithms
real time
model free
levels of abstraction
desirable properties
higher level
dynamic programming
high level
case study
search engine
data mining