List your company

Offline Reinforcement Learning on D4RL Antmaze umaze

100Normalized ScoreFQL
67.2475.74584.2592.755Oct 13, 2025Nov 3, 2025Nov 25, 2025Dec 17, 2025Jan 7, 2026Jan 29, 2026Feb 20, 2026

Evaluation results

MethodLinks
FQL2025.10100
GTP2025.10100
EPQPolicy Type=Gaussian, Seeds=82026.0299.4
FACPolicy Type=Flow, Seeds=82026.0298.5
TD3+BCDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1198.5
MCQPolicy Type=Gaussian, Seeds=82026.0298.3
ReBRACPolicy Type=Gaussian, Seeds=82026.0297.8
QIPO-Diff2025.1097.5
SRPOPolicy Type=Diffusion, Seeds=82026.0297.1
SAC-RNDPolicy Type=Gaussian, Seeds=82026.0297
FQLPolicy Type=Flow, Seeds=82026.0296
CQLDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1194.8
IDQLPolicy Type=Diffusion, Seeds=82026.0294
QIPO-OTPolicy Type=Diffusion, Seeds=82026.0293.6
QIPO-OT2025.1093.6
XQLDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1190.3
QQLDomain=AntMaze, Hyperparameter Tuning=consistent2025.1188.5
MXQLDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1188.3
IQLPolicy Type=Gaussian, Seeds=82026.0287.5
IQLDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1184
TD3+BCPolicy Type=Gaussian, Seeds=82026.0278.6
CACPolicy Type=Diffusion, Seeds=82026.0275.8
CQLPolicy Type=Gaussian, Seeds=82026.0274
BCDomain=AntMaze, Hyperparameter Tuning=individually tuned2025.1168.5