List your company

Offline Reinforcement Learning on D4RL antmaze-large (play)

90Normalized ScoreFAC
-3.620.74569.3Oct 1, 2021Jul 13, 2022Apr 24, 2023Feb 4, 2024Nov 15, 2024Aug 27, 2025Jun 9, 2026

Evaluation results

MethodLinks
FACPolicy Type=Flow, Seeds=82026.0290
FQLPolicy Type=Flow, Seeds=82026.0284
IDQLPolicy Type=Diffusion, Seeds=82026.0263.5
ReBRACPolicy Type=Gaussian, Seeds=82026.0260.4
QIPO-OTPolicy Type=Diffusion, Seeds=82026.0255.5
SRPOPolicy Type=Diffusion, Seeds=82026.0253.6
SAC-RNDPolicy Type=Gaussian, Seeds=82026.0243.9
EPQPolicy Type=Gaussian, Seeds=82026.0240
IQLPolicy Type=Gaussian, Seeds=82026.0239.6
ROMI-CQL2021.1023.6
ROMI-BCQ2021.1020.2
CQLPolicy Type=Gaussian, Seeds=82026.0215.8
MCQPolicy Type=Gaussian, Seeds=82026.022.5
BAIL2021.102.2
BFQPolicy Type=One-Step Flow/Diffusion Policy2026.060.885
OFQLPolicy Type=One-Step Flow/Diffusion Policy2026.060.84
FQLPolicy Type=One-Step Flow/Diffusion Policy2026.060.84
DQLPolicy Type=Diffusion Policy2026.060.833
SAGEMethod Category=Diffusion Planners2026.030.821
DQL*Method Category=Diffusion Policies2026.030.813
DV*Method Category=Diffusion Planners2026.030.764
IDQL*Method Category=Diffusion Policies2026.030.635
SORLPolicy Type=One-Step Flow/Diffusion Policy2026.060.573
CQLMethod Category=Non-Diffusion2026.030.537
SRPOPolicy Type=One-Step Flow/Diffusion Policy2026.060.536
IDQLPolicy Type=Diffusion Policy2026.060.487
IQLMethod Category=Non-Diffusion2026.030.396
IQLPolicy Type=Gaussian Policy2026.060.386
EDPPolicy Type=Diffusion Policy2026.060.333
LoMAPMethod Category=Diffusion Planners2026.030.207
TD3+BCPolicy Type=Gaussian, Seeds=82026.020.2
Diffuser*Method Category=Diffusion Planners2026.030.173
BCQMethod Category=Non-Diffusion2026.030.067
TD3-BCPolicy Type=Gaussian Policy2026.060.002
BC2021.100
BCQ2021.100
CQL2021.100
BEAR2021.100
BRAC-P2021.100
BRAC-v2021.100
MOPO2021.100
MOREL2021.100
Repb-SDE2021.100
COMBO2021.100
CACPolicy Type=Diffusion, Seeds=82026.020
BCMethod Category=IL2026.030
BCPolicy Type=Gaussian Policy2026.060