Reinforcement Learning on MuJoCo (test)
1Fraction of Teacher Scorestudent-distill
Evaluation results
| Method | Links | |
|---|---|---|
| student-distillStudent model size=same-size2024.07 | 1 | |
| PPDStudent model size=same-size2024.07 | 1 | |
| student-distillStudent model size=larger2024.07 | 1 | |
| PPDStudent model size=larger2024.07 | 1 | |
| teacher-distillStudent model size=smaller2024.07 | 0.99 | |
| student-distillStudent model size=smaller2024.07 | 0.99 | |
| PPDStudent model size=smaller2024.07 | 0.99 | |
| teacher-distillStudent model size=same-size2024.07 | 0.99 | |
| teacher-distillStudent model size=larger2024.07 | 0.99 |