Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Online Reinforcement Learning on FishSwim DMControl (final)
Loading...
641.01
Normalized Return
GoRL(FM)
123.6204
257.9427
392.265
526.5873
Dec 2, 2025
Normalized Return
Updated 3mo ago
Evaluation Results
Method
Method
Links
Normalized Return
GoRL(FM)
Seeds=5, Decoder=Flow-...
2025.12
641.01
GoRL(Diff)
Seeds=5, Decoder=Diffu...
2025.12
608.61
PPO
Seeds=5
2025.12
433.7
FPO
Seeds=5
2025.12
204.66
DPPO
Seeds=5
2025.12
143.52
Feedback
Search any
task
Search any
task