Direction on Human study
99Human-likeness Win RateTask Tokens
Evaluation Results
| Method | Links | |
|---|---|---|
| Task TokensWins v.s. Algorithm=MaskedMimic Fine-Tune2025.03 | 99 | |
| Task TokensWins v.s. Algorithm=PPO2025.03 | 99 | |
| Task TokensWins v.s. Algorithm=MaskedMimic F.T. + J.C.2025.03 | 96 | |
| Task TokensWins v.s. Algorithm=MaskedMimic (J.C. only)2025.03 | 95 | |
| Task TokensWins v.s. Algorithm=AMP2025.03 | 92 | |
| Task TokensWins v.s. Algorithm=PULSE2025.03 | 15 |