List your company

Locomotion on D4RL walker2d-medium-expert

5,421.3Normalized ScoreUni-O4
-193.2441,264.3782,7224,179.622Oct 15, 2022May 21, 2023Dec 26, 2023Jul 31, 2024Mar 7, 2025Oct 11, 2025May 18, 2026

Evaluation results

MethodLinks
Uni-O42026.055,421.3—
Onestep RL2026.055,189.1—
Cal-QL2026.055,102.7—
TD3+BC2026.055,056—
COOPO2026.055,042.8—
IQL2026.055,033—
CQL2026.054,996.3—
BC2026.054,936.6—
AWAC2026.054,643.2—
Off2ON2026.053,934.8—
PEX2026.053,205.1—
ODT2026.053,040—
O2PPOOnline update way=IQL2024.12121.49.35
O2SACOnline update way=SAC2024.12120.9511.51
Off2OnOnline update way=SAC2024.12118.018.51
One-step RLMethod Category=Weighted BC, Seeds=52022.10113—
OFQLCategory=One-step Flow Policies2025.08113—
A2PO2024.03112.1—
DMEMM2026.02111.6—
PRDC2024.03111.2—
IDQLCategory=Multi-step Diffusion Policies2025.08110.6—
IQL+ReD2024.03110.5—
EDPCategory=Multi-step Diffusion Policies2025.08110.4—
BiTrajDiffRL Algorithm=CQL2025.06110.4—
BaseRL Algorithm=CQL2025.06110.2—
TD3+BCMethod Category=Best RL Baseline, Seeds=52022.10110.1—
TD3-BCCategory=Non-Diffusion Policies2025.08110.1—
DQLCategory=Multi-step Diffusion Policies2025.08110.1—
RTDiffRL Algorithm=CQL2025.06110.1—
SyntherRL Algorithm=CQL2025.06110.1—
IQLMethod Category=Weighted BC, Seeds=52022.10109.6—
IQL2023.12109.6—
IQL2026.02109.6—
IQLCategory=Non-Diffusion Policies2025.08109.6—
IQL2026.02109.6—
IQL2026.03109.6—
SAGE2026.03109.4—
DiffStitchRL Algorithm=CQL2025.06109.4—
LDCQ2026.03109.3—
LoMAP2026.03109.2—
PORMethod Category=Conditioned BC, Seeds=52022.10109.1—
ISCTSeeds=5, Episodes=102026.02109.1—
10%BCMethod Category=Weighted BC, Seeds=52022.10109—
%BC2024.03109—
DD2023.12108.8—
CQL2026.02108.8—
CQL2026.02108.8—
CQL2026.03108.8—
DVreproduced=true2026.03108.6—
Diffuser2023.12108.4—
DDCategory=Diffusion Planners2025.08108.4—
DTAMP2023.12108.2—
DTMethod Category=Conditioned BC, Seeds=52022.10108.1—
DT2023.12108.1—
DT2024.03108.1—
DT2026.02108.1—
DT2026.02108.1—
DT2026.03108.1—
HDMI2026.02107.9—
IMLE+Exp RW2026.03107.9—
RGG2026.03107.8—
CQL2023.12107.5—
BCCategory=Non-Diffusion Policies2025.08107.5—
BC2026.02107.5—
BC2026.03107.5—
DiffuserCategory=Diffusion Planners2025.08107.4—
HD-DA2026.02107.1—
Diffuser2026.02106.9—
Diffuserreproduced=true2026.03106.9—
Diffuser2026.03106.9—
BiTrajDiffRL Algorithm=DT2025.06106.3—
RvSMethod Category=Conditioned BC, Seeds=52022.10106—
SyntherRL Algorithm=DT2025.06105.7—
BaseRL Algorithm=DT2025.06104.6—
DiffStitchRL Algorithm=DT2025.06104—
TT2023.12101.9—
TT2026.02101.9—
TT2026.03101.9—
RTDiffRL Algorithm=DT2025.06101.2—
TD3+BC2026.02101.1—
FQLCategory=One-step Flow Policies2025.08100.5—
BestPhase=Offline2026.05100—
OEPhase=Online, Online Interaction Budget=320 K2026.05100—
Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.0596.7—
MOReL2026.0295.6—
MOReL2026.0395.6—
MBOP2026.0370.2—
MOPO2026.0344.6—
FTPhase=Online, Online Interaction Budget=320 K2026.0528—
OPEPhase=Offline2026.0522.7—