Flappy
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Continual Reinforcement Learning | Flappy Task 5 | Final Transfer Grand Average (F-bar)1.05 | 9 | |
| Continual Reinforcement Learning | Flappy Task 4 | Final Transfer Grand Average (F-bar)1.45 | 9 | |
| Continual Reinforcement Learning | Flappy Task 3 | Final Transfer Grand Average (F-bar)1.19 | 9 | |
| Continual Reinforcement Learning | Flappy Task 5 | Worst Transfer Average (W_bar)0.01 | 9 | |
| Continual Reinforcement Learning | Flappy Task 4 | Worst Transfer Grand Average (W_bar)0.26 | 9 | |
| Continual Reinforcement Learning | Flappy Task 3 | Worst Transfer Average (W_bar)-0.07 | 9 | |
| Continual Reinforcement Learning | Flappy Task 2 | Worst Transfer Grand Average (W_bar)-0.12 | 9 | |
| Continual Reinforcement Learning | Flappy Task 1 | Worst Transfer Average (W_bar)-0.15 | 9 | |
| Reinforcement Learning | Flappy Task 5 | Grand Average Return (G)9.55 | 9 | |
| Reinforcement Learning | Flappy Task 4 | Grand Average Return18.01 | 9 | |
| Reinforcement Learning | Flappy Task 3 | Grand Average Return32.29 | 9 | |
| Reinforcement Learning | Flappy Task 2 | Grand Average Return (G)54.31 | 9 | |
| Reinforcement Learning | Flappy Task 1 | Grand Average Return (G)94.53 | 9 |
Showing 13 of 13 rows