A framework that fuses uncertain human advice, encoded as subjective logic opinions, into the policy of a reinforcement learning agent improves learning of model transformation sequences, but only convincingly at low-to-moderate advice uncertainty.
Parmorel: A framework for customizable model repair,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance
A framework that fuses uncertain human advice, encoded as subjective logic opinions, into the policy of a reinforcement learning agent improves learning of model transformation sequences, but only convincingly at low-to-moderate advice uncertainty.