RL-HGGA uses tabular Q-learning to select among eight macro-actions in HGGA for 1D bin packing, matching solution quality at 50x lower runtime on Falkenauer, Scholl, and Hard28 instances.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hybridizing a Grouping Metaheuristic with Reinforcement Learning for the One-Dimensional Bin Packing Problem
RL-HGGA uses tabular Q-learning to select among eight macro-actions in HGGA for 1D bin packing, matching solution quality at 50x lower runtime on Falkenauer, Scholl, and Hard28 instances.