List your company

Continuous Control on DM Control pendulum-swingup

0.56Average RewardRC-SAC
0.48720.50610.5250.5439Mar 5, 2026

Evaluation results

MethodLinks
RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.56
RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.030.53
TD3training steps=50 [k], seeds=3, w_target=0.52026.030.49
SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.49