List your company

Offline Reinforcement Learning on D4RL Medium Hopper

109.4Normalized ScoreRRPI
24.74446.72268.790.678Jun 9, 2023Dec 3, 2023May 28, 2024Nov 22, 2024May 18, 2025Nov 11, 2025May 8, 2026

Evaluation results

MethodLinks
RRPINumber of random seeds=42026.03109.4
PSPOAveraged across=4 random seeds2026.05108.5
AMGNumber of random seeds=42026.03107.4
ADM2026.05107.4
PMDBNumber of random seeds=42026.03106.8
PMDBMethod Type=Model-based2023.10106.8
PMDB2026.05106.8
CABI+TD3-BCMethod Type=Model-based2023.10105
Count-MORLMethod Type=Model-based2023.10103.6
CROPMethod Type=Model-based2023.10102.1
EDACMethod Type=Model-free2023.10101.6
EPQNumber of random seeds=42026.03101.3
EPQ2026.05101.3
DMGNumber of random seeds=42026.03100.6
DMG2026.05100.6
DMambasource=Lv et al., 20242023.0698.5
MPDiffuser+Rankranking=true2025.1298.4
MPDiffuserranking=false2025.1297.9
Planner2025.1297.6
COMBO2025.1297.2
COMBOMethod Type=Model-based2023.1097.2
MOREL2023.0695.4
MOReL2026.0395.4
RAMBOMethod Type=Model-based2023.1092.8
DQLNFE=52026.0390.5
KDPNFE=12026.0390.3
RAMBONumber of random seeds=42026.0387
RAMBO2026.0587
MambaDM2023.0685.7
ATACMethod Type=Model-free2023.1085.6
MOReLNumber of random seeds=42026.0384
MOReL2026.0584
DMambasource=Ota, 20242023.0683.5
DDImplementation=reproduced2023.0681.2
CACNFE=22026.0380.7
DDImplementation=Original2023.0679.3
Decision Diffuser2025.1279.3
RATE2023.0677.4
Decision Stacks2023.0676.6
DiffuserNFE=202026.0374.3
CBCNFE=22026.0371.7
DT2023.0667.6
DT2025.1267.6
DT2023.0667.6
DT2026.0367.6
IQL2023.0666.3
IQL2026.0366.3
IQLMethod Type=Model-free2023.1066.3
TAP2023.0663.4
DT2023.0663.1
IDQL2025.1263.1
Diffuser2023.0662.2
CQLNumber of random seeds=42026.0361.9
CQL2026.0561.9
D-MPC2025.1261.2
TT2023.0661.1
TT2023.0661.1
TT2026.0361.1
CQL2023.0658.5
Diffuser2023.0658.5
Diffuser2025.1258.5
CQL2026.0358.5
CQL2023.0658
Decision Stacks2023.0657.7
TT2023.0655.7
BC2023.0652.9
BC2025.1252.9
BC2026.0352.9
MBOP2026.0348.8
DD2023.0638.1
BC2023.0636.4
MOPO2026.0328