List your company

Continuous Control on DM Control fish-swim

0.51Average RewardTD3
0.37480.40990.4450.4801Mar 5, 2026

Evaluation results

MethodLinks
TD3training steps=50 [k], seeds=3, w_target=0.52026.030.51
RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.48
SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.47
RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.030.38