ResearchBenchmarksReinforcement Learning on Ant 1.5 gravity MuJoCoFollow3,472RewardDARAIL889.681,560.092,230.52,900.91Nov 15, 2024Evaluation ResultsMethodMethodLinksRewardDARAIL2024.113,472IS-ACL2024.112,396GARAT2024.111,961IS-R2024.111,712MATL2024.111,376DAIL2024.11990MBPO2024.11989