ResearchBenchmarksCombinatorial Reinforcement Learning on Dynamic InterventionFollow17.21RewardLSFLOW8.57810.81913.0615.301Jan 29, 2026Evaluation ResultsMethodMethodLinksRewardLSFLOWAvg. Time (h)=1.29Avg. Time (h)=1.292026.0117.21DQN-SamplingAvg. Time (h)=0.52Avg. Time (h)=0.522026.0115.16SRLAvg. Time (h)=3.89Avg. Time (h)=3.892026.0113.36SEQUOIAAvg. Time (h)=9.11Avg. Time (h)=9.112026.0110.84Greedy2026.0110.55Random2026.018.91