List your company

Locomotion on D4RL Hopper-medium

100.42Normalized ScoreO2PPO
25.103244.656664.2183.7634Dec 25, 2024Mar 9, 2025May 22, 2025Aug 4, 2025Oct 17, 2025Dec 30, 2025Mar 14, 2026

Evaluation results

MethodLinks
O2PPOOnline update way=IQL2024.12100.4248.61
O2TD3Online update way=TD32024.12100.2543.95
ACAOnline update way=SAC2024.1299.7641.08
TD3+BC2026.0299.5—
O2SACOnline update way=SAC2024.1297.2938
PEXOnline update way=IQL2024.1295.733.59
MOReL2026.0395.4—
LoMAP2026.0393.7—
Cal-QLOnline update way=SAC2024.1292.8333.92
Off2OnOnline update way=SAC2024.1290.3429.83
IMLE+Exp RW2026.0385—
SAGE2026.0383.9—
RGG2026.0382.5—
AWACOnline update way=IQL2024.1282.4216.53
DVreproduced=true2026.0380.9—
Diffuserreproduced=true2026.0374.3—
Diffuser2026.0374.3—
DT2026.0267.6—
DT2026.0367.6—
IQL2026.0266.3—
IQL2026.0366.3—
LDCQ2026.0366.2—
TT2026.0361.1—
IQLOnline update way=IQL2024.1260.48-1.62
ISCTSeeds=5, Episodes=102026.0258.8—
CQL2026.0258.5—
CQL2026.0358.5—
BC2026.0352.9—
MBOP2026.0348.8—
MOPO2026.0328—