2 papers
cs.LG2025
Unraveling the Rainbow: can value-based methods schedule?
Arthur Corrêa, Alexandre Jesus, Paulo Nascimento +2
In this work, we conduct an extensive empirical study of several deep reinforcement learning algorithms on two challenging combinatorial optimization problems: the job-shop and fle…
cs.LG2025
TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problems
Arthur Corrêa, Cristóvão Silva, Liming Xu +2
This paper introduces TuneNSearch, a hybrid transfer learning and local search approach for addressing diverse variants of the vehicle routing problem (VRP). Our method uses reinfo…