Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data.

Martin Tappler Andrea Pferscher Bernhard K. Aichernig Bettina Könighofer

Published in: ICSE (2024)

Keyphrases

reinforcement learning
learning algorithm
data collection
data analysis
learning process
prior knowledge
data sets
training data
data processing
supervised learning
learning models
raw data
missing data
database
data points
data mining techniques
human experts
image data
markov decision processes
policy search