Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL AntMaze v0 (medium-play)
Loading...
88.1
Normalized Score
OFQL
-3.524
20.263
44.05
67.837
Jun 12, 2021
Apr 11, 2022
Feb 9, 2023
Dec 10, 2023
Oct 9, 2024
Aug 9, 2025
Jun 9, 2026
Normalized Score
Updated 7d ago
Evaluation Results
Method
Method
Links
Normalized Score
OFQL
Policy Type=One-Step F...
2026.06
88.1
BFQ
Policy Type=One-Step F...
2026.06
87
DQL
Policy Type=Diffusion...
2026.06
86
GTP
2025.10
83.3
QIPO-Diff
2025.10
82.8
SRPO
Policy Type=One-Step F...
2026.06
80.7
SORL
Policy Type=One-Step F...
2026.06
80.1
QIPO-OT
2025.10
80
FQL
Policy Type=One-Step F...
2026.06
78
IQL
Policy Type=Gaussian P...
2026.06
75.5
EDP
Policy Type=Diffusion...
2026.06
73.3
IDQL
Policy Type=Diffusion...
2026.06
67.3
TD3-BC
Policy Type=Gaussian P...
2026.06
10.6
TD3+BC
Evaluations=final 10,...
2021.06
3
BC
Policy Type=Gaussian P...
2026.06
0
Feedback
Search any
task
Search any
task