List your company

Offline Reinforcement Learning on D4RL Hopper-medium-expert v2

116.5Normalized ReturnPhyB
3.45232.80162.1591.499Feb 13, 2022Nov 1, 2022Jul 20, 2023Apr 6, 2024Dec 23, 2024Sep 10, 2025May 30, 2026

Evaluation results

MethodLinks
PhyBModel category=Model-based2026.05116.5
ADMModel category=Model-based2026.05112.7
TD3+BCModel category=Model-free2026.05112.2
PMDB2022.10111.8
PMDBN=10, k=22022.10111.8
PMDBModel category=Model-based2026.05111.8
Uncertainty-Aware Rank-One MIMO Q Network2026.02111.6
PBRL2026.02110.8
EDAC2022.10110.7
EDAC2022.10110.7
BCQ2026.02110.5
DMGModel category=Model-free2026.05110.4
EPQModel category=Model-free2026.05108.8
DT2022.02107.6
DT2023.01107.6
MOREL2022.10105.6
MOReL2022.10105.6
CQL2026.02105.6
MOReLModel category=Model-based2026.05105.6
CQL2022.02105.4
CQL2023.01105.4
Onestep2022.02103.3
Onestep RL2023.01103.3
SPOT2022.0299.3
SPOT2023.0199.3
TD3+BC2022.0298
TD3+BC2023.0198
TD3-BC2026.0298
CQL2022.1096.9
CQL2022.1096.9
CQLModel category=Model-free2026.0596.9
CPED2023.0195.3
IQL2022.0291.5
IQL2023.0191.5
IQL2026.0291.5
FQL+BCTraining timesteps=1M, Random seeds=102025.0990.29
RAMBO2022.1088.2
RAMBOModel category=Model-based2026.0588.2
BRAC2022.1081.3
BRAC2022.1081.3
IQLTraining timesteps=1M, Random seeds=102025.0973.16
BEAR2022.1066.2
BEAR2022.1066.2
MOPO2026.0260.6
OTDFShift Type=Kinematic2025.1258.1
EDAC-102026.0258.1
AWAC2022.0255.8
AWAC2023.0155.8
DROCOShift Type=Kinematic2025.1254
BC2022.1053.9
BC2022.1053.9
BC2022.0252.5
BC2023.0152.5
BEAR2026.0250.6
BOSAShift Type=Kinematic2025.1249.6
UWAV2026.0244.9
FQLModel category=Model-free2026.0543.8
DARAShift Type=Kinematic2025.1217
IQLShift Type=Kinematic2025.1212.5
IGDFShift Type=Kinematic2025.1211.6
CQLShift Type=Kinematic2025.127.8