Offline Reinforcement Learning on D4RL Walker-medium-expert v2 benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on D4RL Walker-medium-expert v2

113Normalized ReturnOnestep

Evaluation Results

Method	Links
Onestep2022.02		113
SPOT2022.02		112
VDT2026.01		110.4
TD3+BC2022.02		110.1
TD3+BC2026.01		110.1
LSDT2026.01		109.8
IQL2022.02		109.6
IQL2026.01		109.6
DDT2026.01		109.5
CQL2022.02		108.8
DT2026.01		108.6
DT2022.02		108.1
BC2022.02		107.5
CQL2026.01		98.7
BRAC-v2026.01		81.6
AWAC2022.02		74.5