ResearchBenchmarksCombinatorial Reinforcement Learning on Dynamic SchedulingFollow28.85RewardLSFLOW9.370814.427919.48524.5421Jan 29, 2026Evaluation ResultsMethodMethodLinksRewardLSFLOWAvg. Time (h)=1.29Avg. Time (h)=1.292026.0128.85SRLAvg. Time (h)=3.89Avg. Time (h)=3.892026.0124.5SEQUOIAAvg. Time (h)=9.11Avg. Time (h)=9.112026.0124DQN-SamplingAvg. Time (h)=0.52Avg. Time (h)=0.522026.0116.89Greedy2026.0115.12Random2026.0110.12