Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-Online Reinforcement Learning on hammer-cloned v1
Loading...
46.74
Average Online Expected Return
DUAL
-1.5992
10.9504
23.5
36.0496
May 29, 2026
Average Online Expected Return
Updated 2d ago
Evaluation Results
Method
Method
Links
Average Online Expected Return
DUAL
Critic framework=IQL,...
2026.05
46.74
Diff-QL
Critic framework=IQL,...
2026.05
33.82
EDIS
Critic framework=IQL,...
2026.05
28
Base
Critic framework=IQL,...
2026.05
27.41
DUAL
Critic framework=Cal-Q...
2026.05
0.68
EDIS
Critic framework=Cal-Q...
2026.05
0.35
Diff-QL
Critic framework=Cal-Q...
2026.05
0.32
Base
Critic framework=Cal-Q...
2026.05
0.26
Feedback
Search any
task
Search any
task
