Reinforcement learning fine-tuning with numerical fitness rewards improves equation discovery accuracy and noise robustness of a pretrained symbolic regression transformer.
Multiple regression genetic programming
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
Reinforcement learning fine-tuning with numerical fitness rewards improves equation discovery accuracy and noise robustness of a pretrained symbolic regression transformer.