Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Generative Recommendation on RecSim Medium Quality Mixed Strategy
Loading...
0.374
Reward
DRPO
0.21592
0.25696
0.298
0.33904
Feb 11, 2026
Reward
eCPM
Updated 4d ago
Evaluation Results
Method
Method
Links
Reward
eCPM
DRPO
2026.02
0.374
1.87
DRPO-Exp
2026.02
0.372
1.86
Adapt. BC
mechanism=Adaptive fil...
2026.02
0.367
1.84
BPPO
2026.02
0.341
1.7
BC
2026.02
0.338
1.69
IQL
2026.02
0.337
1.68
AWR
2026.02
0.333
1.66
CRR
2026.02
0.222
1.11
Feedback
Search any
task
Search any
task