ResearchBenchmarksReinforcement Learning on Walker2d 1.5 gravity MuJoCoFollow4,409RewardDARAIL369.641,418.322,4673,515.68Nov 15, 2024Evaluation ResultsMethodMethodLinksRewardDARAIL2024.114,409IS-R2024.111,543MATL2024.111,419IS-ACL2024.111,369MBPO2024.11870GARAT2024.11630DAIL2024.11525