List your company

Offline Reinforcement Learning on D4RL v2 (MuJoCo M/MR/ME + Adroit Tasks)

87.6Average ScoreDOIT
12.61632.08351.5571.017Jan 28, 2026Jan 31, 2026Feb 4, 2026Feb 7, 2026Feb 11, 2026Feb 14, 2026Feb 18, 2026

Evaluation results

MethodLinks
DOITmethod_type=Inference-time2026.0287.6————————————
QGPOmethod_type=Training-time2026.0286.69896.910854.147.693.58684.4110.7———
D-QLmethod_type=Training-time2026.0286.382.4100.7110.750.647.596.185.194.3109.7———
TTSmethod_type=Inference-time2026.0286.1————————————
TFGmethod_type=Inference-time2026.0282.1————————————
DASmethod_type=Inference-time2026.0280.2————————————
IQLmethod_type=Training-time2026.0276.966.394.791.547.444.286.778.373.9109.6———
Diffusermethod_type=Training-time2026.0275.358.596.8107.244.242.279.879.761.2108.4———
C4samples=≤10k2026.0158.169.245.981.346.343.146.965.955.496.355.585.35.8
BPPOsamples=≤10k2026.0149.55545.127.928.534.422.354.729.561.391.5117.825.9
TSRLsamples=≤10k2026.0138.960.923.556.643.327.737.247.327.650.95.785.70.3
IQLsamples=≤10k2026.0135.86116.251.735.634.114.334.217.7385171.54.3
CQLsamples=≤10k2026.0131.850.113.243.241.716.339.754.113.82631.341.210.7
DOGEsamples=≤10k2026.0130.955.619.136.842.826.333.153.715.542.510.235.8-1.1
A2PRsamples=≤10k2026.0126.355.912.549.737.123.632.45.934.456.58.3-0.1-0.3
BCsamples=≤10k2026.0124.428.819.738.240.225.233.725.42.535.133.89.50.6
TD3BCsamples=≤10k2026.0115.530.711.322.625.929.123.511.29.312.409.50.6