ResearchBenchmarksReinforcement Learning on Ant target domain 1.5 densityReinforcement Learning on Ant target domain 1.5 densityFollow6,036RewardDARC3,178.083,920.044,6625,403.96Nov 15, 2024Evaluation resultsMethodMethodLinksRewardDARCProtocol=TrainingProtocol=Training2024.116,036DARCProtocol=EvaluationProtocol=Evaluation2024.115,961DARAIL2024.115,193OptimalContext=Optimal in TargetContext=Optimal in Target2024.113,288