List your company

Locomotion on D4RL halfcheetah-medium-expert (Test Return)

9,242.2Test ReturnCOOPO
-295.9522,180.2994,656.557,132.801Jun 6, 2025Aug 2, 2025Sep 29, 2025Nov 26, 2025Jan 22, 2026Mar 21, 2026May 18, 2026

Evaluation results

MethodLinks
COOPO2026.059,242.2
Onestep RL2026.058,949.3
Uni-O42026.058,859.3
Cal-QL2026.058,782.9
CQL2026.058,762.8
TD3+BC2026.058,674.5
IQL2026.058,278.3
BC2026.055,192.7
Off2ON2026.054,333
AWAC2026.053,976.5
ODT2026.053,566.1
PEX2026.052,778.3
BiTrajDiffRL Algorithm=CQL2025.0694.1
SyntherRL Algorithm=CQL2025.0692.2
DiffStitchRL Algorithm=CQL2025.0691.4
RTDiffRL Algorithm=CQL2025.0690
BaseRL Algorithm=CQL2025.0687.2
BiTrajDiffRL Algorithm=DT2025.0683.5
SyntherRL Algorithm=DT2025.0680.4
DiffStitchRL Algorithm=DT2025.0676.9
RTDiffRL Algorithm=DT2025.0672.3
BaseRL Algorithm=DT2025.0670.9