ResearchBenchmarksContinuous Control on DM Control ball-in-cup-catchFollow0.94Average RewardRC-TD30.82560.85530.8850.9147Mar 5, 2026Evaluation ResultsMethodMethodLinksAverage RewardRC-TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.52026.030.94SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.52026.030.92RC-SACtraining steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.52026.030.92TD3training steps=50 [k],...training steps=50 [k], seeds=3, w_target=0.52026.030.83