Reinforcement Learning on Atari (test)
1.1Fraction of Teacher ScorePPD
Evaluation Results
| Method | Links | |
|---|---|---|
| PPDStudent model size=larger2024.07 | 1.1 | |
| student-distillStudent model size=larger2024.07 | 1.09 | |
| PPDStudent model size=same-size2024.07 | 1.08 | |
| student-distillStudent model size=same-size2024.07 | 1.07 | |
| teacher-distillStudent model size=larger2024.07 | 1.07 | |
| teacher-distillStudent model size=same-size2024.07 | 1 | |
| PPDStudent model size=smaller2024.07 | 0.97 | |
| student-distillStudent model size=smaller2024.07 | 0.94 | |
| teacher-distillStudent model size=smaller2024.07 | 0.86 |