ResearchBenchmarksRobotic Manipulation on ManiSkill3 LiftPegUprightMO v1Follow0.65Average RewardRC-SAC0.34840.42670.5050.5833Mar 5, 2026Evaluation ResultsMethodMethodLinksAverage RewardRC-SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.65SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.6RC-TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.43TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.252026.030.36