List your company

Offline Reinforcement Learning on D4RL Maze2D Large

200.6Normalized PerformanceSAGE
-7.97246.1765100.325154.4735May 29, 2024Sep 30, 2024Feb 1, 2025Jun 5, 2025Oct 7, 2025Feb 8, 2026Jun 12, 2026

Evaluation results

MethodLinks
SAGEMethod Category=Diffusion Planners2026.03200.6
DV*Method Category=Diffusion Planners2026.03197.4
DQL*Method Category=Diffusion Policies2026.03186.8
LoMAPMethod Category=Diffusion Planners2026.03151.9
LDCQMethod Category=Diffusion Planners2026.03150.1
RGGMethod Category=Diffusion Planners2026.03148.3
Diffuser*Method Category=Diffusion Planners2026.03123
IDQL*Method Category=Diffusion Policies2026.0390.1
TD3+BCSeeds=52026.0688.6
DRIVESeeds=52026.0684.4
BEARSeeds=52026.0681
DiffStitchAlgorithm=CQL, Augmentation Method=DiffStitch2025.0665.2
IQLSeeds=52026.0661.7
IQLMethod Category=Non-Diffusion2026.0358.6
CQLSeeds=52026.0649.6
BiTrajDiffAlgorithm=CQL, Augmentation Method=Ours2025.0648.3
SyntherAlgorithm=CQL, Augmentation Method=Synther2025.0645.3
PDiTSeeds=52026.0640
RTDiffAlgorithm=CQL, Augmentation Method=RTDiff2025.0638.9
BaseAlgorithm=CQL, Augmentation Method=Base2025.0634.3
BiTrajDiffAlgorithm=DT, Augmentation Method=Ours2025.0628.5
DTSeeds=52026.0625.4
RTDiffAlgorithm=DT, Augmentation Method=RTDiff2025.0624.9
DiffStitchAlgorithm=DT, Augmentation Method=DiffStitch2025.0624.4
SyntherAlgorithm=DT, Augmentation Method=Synther2025.0624.2
BaseAlgorithm=DT, Augmentation Method=Base2025.0622.3
CQLMethod Category=Non-Diffusion2026.0312.5
BCSeeds=52026.0610.3
BCQMethod Category=Non-Diffusion2026.036.2
BCMethod Category=IL2026.035
DyDiffBase Policy=DiffQL2024.051.99
DyDiffBase Policy=TD3BC2024.051.96
DyDiffBase Policy=CQL2024.051.48
SynthERBase Policy=DiffQL2024.051.38
DiffQLAugmentation=None2024.051.09
SynthERBase Policy=TD3BC2024.050.98
TD3BCAugmentation=None2024.050.43
SynthERBase Policy=CQL2024.050.37
CQLAugmentation=None2024.050.05