Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mapping on Mapping H2
Loading...
4,765.2
Mean Episode Reward
Shared Policy
4,681.376
4,703.138
4,724.9
4,746.662
Apr 5, 2026
Mean Episode Reward
Updated 12d ago
Evaluation Results
Method
Method
Links
Mean Episode Reward
Shared Policy
Budget (B)=200,000, Se...
2026.04
4,765.2
Local Fine-Tuning
Budget (B)=200,000, Se...
2026.04
4,758.2
DC-Ada
Budget (B)=200,000, Se...
2026.04
4,717.6
Random Perturbation
Budget (B)=200,000, Se...
2026.04
4,694.5
Obs. Normalization
Budget (B)=200,000, Se...
2026.04
4,684.6
Feedback
Search any
task
Search any
task