Offline Reinforcement Learning on D4RL walker-medium-replay v2 (test) benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on D4RL walker-medium-replay v2 (test)

82.3Normalized RewardVDT

Evaluation Results

Method	Links
VDT2026.01		82.3
TD3+BC2026.01		81.8
DDT2026.01		77.6
LSDT2026.01		74.7
IQL2026.01		73.9
DT2026.01		66.9
CQL2026.01		26.7
BRAC-v2026.01		0.9
TD3+BC2026.01		0.837
VDT2026.01		0.816
BRAC-v2026.01		0.811
LSDT2026.01		0.81
CQL2026.01		0.792
DDT2026.01		0.786
IQL2026.01		0.783
DT2026.01		0.743