List your company

Locomotion on D4RL walker2d-medium-expert v2

112.62Average Online ReturnDUAL
27.943249.926671.9193.8934May 29, 2026May 31, 2026Jun 3, 2026Jun 6, 2026Jun 9, 2026Jun 12, 2026Jun 15, 2026

Evaluation results

MethodLinks
DUALTime steps=1M, Number of random seeds=52026.05112.62
Diff-QLTime steps=1M, Number of random seeds=52026.05112.48
DACERTime steps=1M, Number of random seeds=52026.05112.43
DiffuserTime steps=1M, Number of random seeds=52026.05111.87
IQLTime steps=1M, Number of random seeds=52026.05111.52
EDISTime steps=1M, Number of random seeds=52026.05111.02
IQL+GT2026.06109.9
LiRE2026.06109.7
Oracle2026.06109.6
VOTP2026.06108.1
P-IQL2026.06103.4
SURF2026.06103.2
IPL2026.0692.4
FTB2026.0676.5
DPPO2026.0670.2
CPL2026.0639.9
APPO2026.0631.2