List your company

Offline Reinforcement Learning on D4RL Medium Walker2d

106.4Normalized ScoreNEUBAY
30.06449.88269.789.518Jun 9, 2023Dec 3, 2023May 28, 2024Nov 22, 2024May 18, 2025Nov 11, 2025May 8, 2026

Evaluation results

MethodLinks
NEUBAYMethod Category=Ours2025.12106.4
PSPOAveraged across=4 random seeds2026.05103.9
RRPINumber of random seeds=42026.0397.5
CBOPMethod Category=Bayesian-inspired2025.1295.5
CROPMethod Type=Model-based2023.1095.4
MoMoMethod Category=Conservative model-based2025.1295
PMDBNumber of random seeds=42026.0394.2
PMDBMethod Type=Model-based2023.1094.2
PMDB2026.0594.2
SUMOMethod Category=Conservative model-based2025.1294.1
ADMPOMethod Category=Conservative model-based2025.1293.2
AMGNumber of random seeds=42026.0393.2
ADM2026.0593.2
VIPOMethod Category=Conservative model-based2025.1293.1
EDACMethod Category=Model-free2025.1292.5
EDACMethod Type=Model-free2023.1092.5
DMGNumber of random seeds=42026.0392.4
DMG2026.0592.4
APE-VMethod Category=Conservative model-based2025.1290.3
ATACMethod Type=Model-free2023.1089.6
EPQNumber of random seeds=42026.0387.8
EPQ2026.0587.8
MOBILEMethod Category=Conservative model-based2025.1287.7
Count-MORLMethod Type=Model-based2023.1087.6
KDPNFE=12026.0387.2
DQLNFE=52026.0387
RAMBOMethod Type=Model-based2023.1086.9
RAMBOMethod Category=Model-free2025.1285
RAMBONumber of random seeds=42026.0384.9
RAMBO2026.0584.9
AdaptDiffuserCategory=Diffusion Planner2024.0584.7
MOPOMethod Category=Conservative model-based2025.1284.1
TD3+BCModel Category=Value-based2026.0283.7
Decision Stacks2023.0683.6
DMMModel Category=SSM-based2026.0283.6
CACNFE=22026.0383.1
CBCNFE=22026.0383.1
DDImplementation=Original2023.0682.5
DDCategory=Diffusion Planner2024.0582.5
Decision Diffuser2025.1282.5
CABI+TD3-BCMethod Type=Model-based2023.1082
COMBOCategory=Model-based RL2024.0581.9
COMBOMethod Category=Model-free2025.1281.9
COMBO2025.1281.9
COMBOMethod Type=Model-based2023.1081.9
MAPLEMethod Category=Bayesian-inspired2025.1281.3
MoDAPMethod Category=Bayesian-inspired2025.1281.1
RATE2023.0680.7
DMambasource=Lv et al., 20242023.0680.3
IDQL2025.1280.2
DDImplementation=reproduced2023.0679.9
Diffuser2023.0679.7
Diffuser2025.1279.7
DiffuserCategory=Diffusion Planner2024.0579.6
DCModel Category=SSM-based2026.0279.6
DiffuserNFE=202026.0379.6
CQLMethod Category=Model-free2025.1279.5
CQLNumber of random seeds=42026.0379.5
CQL2026.0579.5
TT2023.0679
TT2023.0679
TT2026.0379
IQL2023.0678.3
IQL2026.0378.3
IQLMethod Type=Model-free2023.1078.3
DMambasource=Ota, 20242023.0678.2
MambaDM2023.0678.2
DS4Model Category=SSM-based2026.0278
MOREL2023.0677.8
MORELCategory=Model-based RL2024.0577.8
MOReL2026.0377.8
MPDiffuser+Rankranking=true2025.1277.6
DMModel Category=SSM-based2026.0277.6
MPDiffuserranking=false2025.1277.5
DTModel Category=Transformer-based2026.0276.6
D-MPC2025.1276.2
Planner2025.1275.9
EDTModel Category=Transformer-based2026.0275.8
BC2023.0675.3
BC2025.1275.3
BC2026.0375.3
LEQMethod Category=Conservative model-based2025.1274.9
DT2023.0674
DT2025.1274
DT2023.0674
DT2026.0374
MOReLNumber of random seeds=42026.0372.8
MOReL2026.0572.8
CQL2023.0672.5
CQLModel Category=Value-based2026.0272.5
CQL2023.0672.5
CQL2026.0372.5
QLDTModel Category=Transformer-based2026.0267.1
TAP2023.0664.9
DROCO2025.1260.1
CQL*variant=tuned/reproduced2025.1243.1
MBOP2026.0341
BOSA2025.1240.3
OTDF2025.1240.3
IGDF2025.1233