ResearchBenchmarksRobotic Manipulation on ManiSkill3 PullCubeToolMO v1Follow0.29Average RewardRC-SAC-0.03240.05130.1350.2187Mar 5, 2026Evaluation ResultsMethodMethodLinksAverage RewardRC-SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.29RC-TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.23SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.03-0.02