Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on AntMaze umaze D4RL
Loading...
623
Average Episodic Return
GC-Oracle
54.952
202.426
349.9
497.374
Mar 10, 2024
Jul 15, 2024
Nov 20, 2024
Mar 28, 2025
Aug 2, 2025
Dec 8, 2025
Apr 15, 2026
Average Episodic Return
Updated 3d ago
Evaluation Results
Method
Method
Links
Average Episodic Return
GC-Oracle
2024.03
623
DiSPO
2024.03
593
COMBO
2024.03
574
GC-IQL
2024.03
571
FB
2024.03
469
USFA
2024.03
462
RaMP
2024.03
459
MOPO
2024.03
451
CQL
Learning Phase=Offline RL
2026.04
94
O2O-LSVI
Learning Phase=Offline...
2026.04
85.8
IQL
Learning Phase=Offline RL
2026.04
77
Cal-QL
Learning Phase=Offline...
2026.04
76.8
Feedback
Search any
task
Search any
task