Automatic Testing and Falsification with Dynamically Constrained Reinforcement Learning.

Xin Qin Nikos Aréchiga Andrew Best Jyotirmoy V. Deshmukh

Published in: CoRR (2019)

Keyphrases

reinforcement learning
state space
real time
data driven
semi automatic
decision making
function approximation
databases
learning algorithm
artificial neural networks
action selection
changing environment
markov decision processes
transfer learning
training set
video sequences
artificial intelligence
data sets