List your company

Locomotion on D4RL Hopper-medium-expert

112.2Normalized Score (100k Steps)TD3+BC
50.11266.23182.3598.469Dec 25, 2024Mar 4, 2025May 12, 2025Jul 20, 2025Sep 27, 2025Dec 5, 2025Feb 12, 2026

Evaluation results

MethodLinks
TD3+BC2026.02112.2———
DQLCategory=Multi-step Diffusion Policies2025.08111.1———
EDPCategory=Multi-step Diffusion Policies2025.08110.8———
DDCategory=Diffusion Planners2025.08110.4———
OFQLCategory=One-step Flow Policies2025.08110.2———
IDQLCategory=Multi-step Diffusion Policies2025.08110.1———
BiTrajDiffRL Algorithm=DT2025.06110.1———
ISCTSeeds=5, Episodes=102026.02109.8———
RTDiffRL Algorithm=DT2025.06109.6———
SyntherRL Algorithm=DT2025.06109.2———
DiffStitchRL Algorithm=DT2025.06108.8———
O2PPOOnline update way=IQL2024.12107.618.98——
DT2026.02107.6———
BaseRL Algorithm=DT2025.06107.5———
O2SACOnline update way=SAC2024.12107.423.25——
DiffuserCategory=Diffusion Planners2025.08107.2———
BiTrajDiffRL Algorithm=CQL2025.06105.7———
CQL2026.02105.4———
DiffStitchRL Algorithm=CQL2025.06105.3———
BaseRL Algorithm=CQL2025.06103.5———
SyntherRL Algorithm=CQL2025.06103.2———
RTDiffRL Algorithm=CQL2025.06102.2———
Off2OnOnline update way=SAC2024.1299.4714.65——
TD3-BCCategory=Non-Diffusion Policies2025.0898———
IQL2026.0291.5———
IQLCategory=Non-Diffusion Policies2025.0891.5———
FQLCategory=One-step Flow Policies2025.0886.2———
BCCategory=Non-Diffusion Policies2025.0852.5———
AWAC2026.05———1,339.3
BC2026.05———1,269.7
Cal-QL2026.05———2,596.7
COOPO2026.05———3,575.8
CQL2026.05———2,534.6
Diffuserreproduced=true2026.03——103.3—
DVreproduced=true2026.03——108.8—
IQL2026.05———2,201.3
LDCQ2026.03——113.3—
LoMAP2026.03——110.6—
ODT2026.05———1,556.3
Off2ON2026.05———2,697
Onestep RL2026.05———2,484.6
PEX2026.05———2,196.7
RGG2026.03——109.6—
SAGE2026.03——111.3—
TD3+BC2026.05———2,359.7
Uni-O42026.05———2,683.2