Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Online Reinforcement Learning on DMControl FingerSpin (final)
Loading...
903.92
Normalized Return
GoRL(FM)
22.1352
251.0601
479.985
708.9099
Dec 2, 2025
Normalized Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Normalized Return
GoRL(FM)
Seeds=5, Decoder=Flow-...
2025.12
903.92
GoRL(Diff)
Seeds=5, Decoder=Diffu...
2025.12
844.74
DPPO
Seeds=5
2025.12
694.06
PPO
Seeds=5
2025.12
539.03
FPO
Seeds=5
2025.12
56.05
Feedback
Search any
task
Search any
task