List your company

Continuous Control on DeepMind Control Suite Cheetah Run

836RewardDream-MPC
-33.0032192.6034418.21643.8166Oct 14, 2024Jan 16, 2025Apr 21, 2025Jul 25, 2025Oct 28, 2025Jan 31, 2026May 6, 2026

Evaluation results

MethodLinks
Dream-MPCIntegrate with=Dreamer2026.05836—
Dreamer2026.05751—
Dreamer V32024.10737.70.0337
Dreamer V3 with MLE regularisationMLE regularisation=true2024.10675.20.0283
CEM+policy2026.05674—
Policy+Grad-MPC2026.05591—
PlaNet2026.05535—
SAC+AE2026.05495—
Grad-MPC2026.05438—
RC-SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.62—
TD3training steps=50 [k], seeds=3, w_target=0.52026.030.46—
RC-TD3training steps=50 [k], seeds=3, w_target=0.52026.030.46—
SACtraining steps=50 [k], seeds=3, w_target=0.52026.030.42—