Offline Constrained RLHF on PKU-SafeRLHF 7k (test)
-1.6044Safety Reward (r1)πλ
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| πλPolicy Type=Dual-only learned policy, Jmin=−0.6473, η=0.3, T=10002026.03 | -1.6044 | -0.6287 | 0 |
| Method | Links | |||
|---|---|---|---|---|
| πλPolicy Type=Dual-only learned policy, Jmin=−0.6473, η=0.3, T=10002026.03 | -1.6044 | -0.6287 | 0 |