SORREL combines offline reinforcement learning on suboptimal demonstrations with self-imitation finetuning to learn branching policies that match expert-trained solvers.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch
SORREL combines offline reinforcement learning on suboptimal demonstrations with self-imitation finetuning to learn branching policies that match expert-trained solvers.