ResearchBenchmarksCombinatorial Reinforcement Learning on Dynamic AssignmentFollow35.93RewardLSFLOW12.37418.489524.60530.7205Jan 29, 2026Evaluation ResultsMethodMethodLinksRewardLSFLOWAvg. Time (h)=1.29Avg. Time (h)=1.292026.0135.93SEQUOIAAvg. Time (h)=9.11Avg. Time (h)=9.112026.0132.99SRLAvg. Time (h)=3.89Avg. Time (h)=3.892026.0128.46DQN-SamplingAvg. Time (h)=0.52Avg. Time (h)=0.522026.0122.25Greedy2026.0120.15Random2026.0113.28