List your company

Hopper Locomotion on D4RL hopper medium-replay

105.12Normalized ScoreO2SAC
-3.580824.639652.8681.0804Feb 16, 2021Dec 30, 2021Nov 13, 2022Sep 26, 2023Aug 9, 2024Jun 22, 2025May 6, 2026

Evaluation results

MethodLinks
O2SACOnline update way=SAC2024.12105.1216.15
Off2OnOnline update way=SAC2024.12103.614.93
OFQLCategory=One-step Flow Policies2025.08101.9—
A2PO2024.03101.6—
DQLCategory=Multi-step Diffusion Policies2025.08101.3—
IQL+ReD2024.03101—
DMEMM2026.02100.6—
PRDC2024.03100.1—
DD2023.12100—
DTAMP2023.12100—
HDMI2026.0299.6—
IDQLCategory=Multi-step Diffusion Policies2025.0899.4—
DDCategory=Diffusion Planners2025.0899.2—
PORMethod Category=Conditioned BC, Seeds=52022.1098.9—
One-step RLMethod Category=Weighted BC, Seeds=52022.1097.5—
O2PPOOnline update way=IQL2024.1296.8718.14
Diffuser2023.1296.8—
CQLMethod Category=Best RL Baseline, Seeds=52022.1095—
CQL2026.0295—
CQL2026.0295—
CQL2026.0395—
IQLMethod Category=Weighted BC, Seeds=52022.1094.7—
IQL2023.1294.7—
IQL2026.0294.7—
IQLCategory=Non-Diffusion Policies2025.0894.7—
IQL2026.0294.7—
HD-DA2026.0294.7—
IQL2026.0394.7—
MOREL2021.0293.6—
MOReL2026.0293.6—
Diffuser2026.0293.6—
MOReL2026.0393.6—
Diffuser2026.0393.6—
DiffuserCategory=Diffusion Planners2025.0891.8—
TT2023.1291.5—
TT2026.0291.5—
TT2026.0391.5—
COMBO2021.0289.5—
FQLCategory=One-step Flow Policies2025.0885.4—
IMLE+Exp RW2026.0385—
EDPCategory=Multi-step Diffusion Policies2025.0883—
DTMethod Category=Conditioned BC, Seeds=52022.1082.7—
DT2023.1282.7—
DT2024.0382.7—
DT2026.0282.7—
DT2026.0282.7—
DT2026.0382.7—
Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.0580.3—
10%BCMethod Category=Weighted BC, Seeds=52022.1075.9—
%BC2024.0375.9—
RvSMethod Category=Conditioned BC, Seeds=52022.1073.5—
ISCTSeeds=5, Episodes=102026.0270.5—
MOPO2021.0267.5—
MOPO2026.0367.5—
BestPhase=Offline2026.0566.6—
OEPhase=Online, Online Interaction Budget=320 K2026.0566.1—
FTPhase=Online, Online Interaction Budget=320 K2026.0561.4—
TD3-BCCategory=Non-Diffusion Policies2025.0860.9—
CQL2021.0248.6—
BEAR2021.0233.7—
TD3+BC2026.0231.4—
OPEPhase=Offline2026.0524.8—
CQL2023.1218.1—
BCCategory=Non-Diffusion Policies2025.0818.1—
BC2026.0218.1—
BC2026.0318.1—
MBOP2026.0312.4—
BC2021.0211.8—
SAC-off2021.023.5—
BRAC-p2021.020.6—
BRAC-v2021.020.6—