List your company

Generative Recommendation on RecSim Medium Quality Mixed Strategy

0.374RewardDRPO
0.215920.256960.2980.33904Feb 11, 2026

Evaluation results

MethodLinks
DRPO2026.020.3741.87
DRPO-Exp2026.020.3721.86
Adapt. BCmechanism=Adaptive filtering2026.020.3671.84
BPPO2026.020.3411.7
BC2026.020.3381.69
IQL2026.020.3371.68
AWR2026.020.3331.66
CRR2026.020.2221.11