List your company

Walker2d Locomotion Control on D4RL walker2d medium-replay

106.2Normalized ScoreOFQL
-4.5624.19552.9581.705Feb 16, 2021Dec 30, 2021Nov 13, 2022Sep 26, 2023Aug 9, 2024Jun 22, 2025May 6, 2026

Evaluation results

MethodLinks
OFQLCategory=One-step Flow Policies2025.08106.2——
DQLCategory=Multi-step Diffusion Policies2025.0895.5——
BestPhase=Offline2026.0594.9——
OEPhase=Online, Online Interaction Budget=320 K2026.0594.9——
Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.0592.1——
PRDC2024.0392——
IDQLCategory=Multi-step Diffusion Policies2025.0889.1——
EDPCategory=Multi-step Diffusion Policies2025.0887——
DMEMM2026.0285.8——
SyntherRL Algorithm=CQL2025.0684.8——
BiTrajDiffRL Algorithm=CQL2025.0684.8——
RTDiffRL Algorithm=CQL2025.0684.4——
HD-DA2026.0284.1——
A2PO2024.0382.8——
TT2023.1282.6——
TT2026.0282.6——
TT2026.0382.6——
DiffStitchRL Algorithm=CQL2025.0682.4——
FQLCategory=One-step Flow Policies2025.0882.1——
BaseRL Algorithm=CQL2025.0682.1——
TD3+BCMethod Category=Best RL Baseline, Seeds=52022.1081.8——
TD3-BCCategory=Non-Diffusion Policies2025.0881.8——
HDMI2026.0280.7——
DTAMP2023.1279.5——
IQL+ReD2024.0379.5——
CQL2026.0277.2——
CQL2026.0277.2——
CQL2026.0377.2——
PORMethod Category=Conditioned BC, Seeds=52022.1076.6——
DDCategory=Diffusion Planners2025.0875.6——
DD2023.1275——
IQL2023.1273.9——
IQL2026.0273.9——
IQLCategory=Non-Diffusion Policies2025.0873.9——
IQL2026.0273.9——
IQL2026.0373.9——
IQLMethod Category=Weighted BC, Seeds=52022.1073.8——
Diffuser2026.0270.6——
Diffuser2026.0370.6——
IMLE+Exp RW2026.0369.7——
ISCTSeeds=5, Episodes=102026.0268.9——
DTMethod Category=Conditioned BC, Seeds=52022.1066.6——
DT2023.1266.6——
DT2024.0366.6——
DT2026.0266.6——
DT2026.0266.6——
DT2026.0366.6——
10%BCMethod Category=Weighted BC, Seeds=52022.1062.5——
%BC2024.0362.5——
Diffuser2023.1261.2——
RvSMethod Category=Conditioned BC, Seeds=52022.1060.6——
DiffuserCategory=Diffusion Planners2025.0858.3——
BiTrajDiffRL Algorithm=DT2025.0658.2——
FTPhase=Online, Online Interaction Budget=320 K2026.0556.4——
SyntherRL Algorithm=DT2025.0656.1——
COMBO2021.0256——
DiffStitchRL Algorithm=DT2025.0654.6——
RTDiffRL Algorithm=DT2025.0653.8——
BaseRL Algorithm=DT2025.0652.1——
MOREL2021.0249.8——
MOReL2026.0249.8——
MOReL2026.0349.8——
One-step RLMethod Category=Weighted BC, Seeds=52022.1049.5——
MOPO2021.0239——
MOPO2026.0339——
OPEPhase=Offline2026.0533.8——
CQL2021.0232.6——
CQL2023.1226——
BCCategory=Non-Diffusion Policies2025.0826——
BC2026.0226——
BC2026.0326——
TD3+BC2026.0225.2——
BEAR2021.0219.2——
BC2021.0211.3——
MBOP2026.039.7——
SAC-off2021.021.9——
BRAC-v2021.020.9——
BRAC-p2021.02-0.3——
O2PPOOnline update way=IQL2024.12—90.4311.6
O2SACOnline update way=SAC2024.12—106.0528.75
Off2OnOnline update way=SAC2024.12—102.4320.78