List your company

Continuous Control on DM Control walker-run

0.62Average RewardRC-TD3
0.44320.48910.5350.5809Mar 5, 2026

Evaluation results

MethodLinks
RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.030.62
RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.57
TD3training steps=50 [k], seeds=3, w_target=0.52026.030.47
SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.45