Reach on Human study
89Human-likeness Win RateTask Tokens
Evaluation Results
| Method | Links | |
|---|---|---|
| Task TokensWins v.s. Algorithm=PPO2025.03 | 89 | |
| Task TokensWins v.s. Algorithm=MaskedMimic Fine-Tune2025.03 | 85 | |
| Task TokensWins v.s. Algorithm=MaskedMimic F.T. + J.C.2025.03 | 82 | |
| Task TokensWins v.s. Algorithm=AMP2025.03 | 70 | |
| Task TokensWins v.s. Algorithm=MaskedMimic (J.C. only)2025.03 | 53 | |
| Task TokensWins v.s. Algorithm=PULSE2025.03 | 36 |