ResearchBenchmarksReinforcement Learning on HalfCheetah target domain 1.5 densityReinforcement Learning on HalfCheetah target domain 1.5 densityFollow11,515RewardDARAIL6,100.767,506.388,91210,317.62Nov 15, 2024Evaluation resultsMethodMethodLinksRewardDARAIL2024.1111,515DARCProtocol=TrainingProtocol=Training2024.119,380DARCProtocol=EvaluationProtocol=Evaluation2024.118,833OptimalContext=Optimal in TargetContext=Optimal in Target2024.116,309