List your company

Offline Reinforcement Learning on D4RL antmaze-large (diverse)

88Normalized ScoreFAC
-3.5220.244467.76Oct 1, 2021Jun 27, 2022Mar 23, 2023Dec 17, 2023Sep 11, 2024Jun 7, 2025Mar 3, 2026

Evaluation results

MethodLinks
FACPolicy Type=Flow, Seeds=82026.0288
FQLPolicy Type=Flow, Seeds=82026.0283
SAGEMethod Category=Diffusion Planners2026.0377
DV*Method Category=Diffusion Planners2026.0376
DQL*Method Category=Diffusion Policies2026.0370.6
IDQLPolicy Type=Diffusion, Seeds=82026.0267.9
IDQL*Method Category=Diffusion Policies2026.0367.9
CQLMethod Category=Non-Diffusion2026.0361.2
LDCQMethod Category=Diffusion Planners2026.0357.7
ReBRACPolicy Type=Gaussian, Seeds=82026.0254.4
SRPOPolicy Type=Diffusion, Seeds=82026.0253.6
IQLPolicy Type=Gaussian, Seeds=82026.0247.5
IQLMethod Category=Non-Diffusion2026.0347.5
SAC-RNDPolicy Type=Gaussian, Seeds=82026.0245.7
ROMI-BCQ2021.1041.2
LoMAPMethod Category=Diffusion Planners2026.0339.3
EPQPolicy Type=Gaussian, Seeds=82026.0236.7
QIPO-OTPolicy Type=Diffusion, Seeds=82026.0232.1
ROMI-CQL2021.1031.4
Diffuser*Method Category=Diffusion Planners2026.0327.3
BiTrajDiffAlgorithm=CQL, Augmentation Method=Ours2025.0616
CQLPolicy Type=Gaussian, Seeds=82026.0214.9
SyntherAlgorithm=CQL, Augmentation Method=Synther2025.0612.6
BaseAlgorithm=CQL, Augmentation Method=Base2025.068
MCQPolicy Type=Gaussian, Seeds=82026.027.5
RTDiffAlgorithm=CQL, Augmentation Method=RTDiff2025.065.3
DiffStitchAlgorithm=CQL, Augmentation Method=DiffStitch2025.062.6
BCQMethod Category=Non-Diffusion2026.032.2
BAIL2021.101
DiffStitchAlgorithm=DT, Augmentation Method=DiffStitch2025.060.8
BC2021.100
BCQ2021.100
CQL2021.100
BEAR2021.100
BRAC-P2021.100
BRAC-v2021.100
MOPO2021.100
MOREL2021.100
Repb-SDE2021.100
COMBO2021.100
TD3+BCPolicy Type=Gaussian, Seeds=82026.020
CACPolicy Type=Diffusion, Seeds=82026.020
BCMethod Category=IL2026.030
BaseAlgorithm=DT, Augmentation Method=Base2025.060
RTDiffAlgorithm=DT, Augmentation Method=RTDiff2025.060
SyntherAlgorithm=DT, Augmentation Method=Synther2025.060
BiTrajDiffAlgorithm=DT, Augmentation Method=Ours2025.060