A decision transformer, trained offline on ROI-filtered, early-stopped GP-ensemble rollouts and refined by sparse real evaluations, is proposed as a non-myopic policy for Bayesian optimization.
Towards learn- ing universal hyperparameter optimizers with transformers
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
background 1representative citing papers
citing papers explorer
-
Direct Regret Optimization in Bayesian Optimization
A decision transformer, trained offline on ROI-filtered, early-stopped GP-ensemble rollouts and refined by sparse real evaluations, is proposed as a non-myopic policy for Bayesian optimization.