Imitation Learning on Acrobot v1 (test)
103.67Optimality (%)Gladius
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GladiusTrajs=12025.02 | 103.67 | 32.78 | |
| IQ-learnTrajs=12025.02 | 103.47 | 55.44 | |
| GladiusTrajs=32025.02 | 102.19 | 22.69 | |
| IQ-learnTrajs=32025.02 | 101.28 | 37.51 | |
| BCTrajs=32025.02 | 101.25 | 36.42 | |
| IQ-learnTrajs=102025.02 | 101.1 | 30.4 | |
| GladiusTrajs=72025.02 | 100.67 | 22.3 | |
| IQ-learnTrajs=72025.02 | 100.58 | 30.09 | |
| BCTrajs=12025.02 | 100.56 | 26.71 | |
| GladiusTrajs=102025.02 | 99.07 | 20.58 | |
| BCTrajs=72025.02 | 98.08 | 24.27 | |
| BCTrajs=102025.02 | 97.75 | 16.67 | |
| GladiusTrajs=152025.02 | 96.5 | 18.53 | |
| IQ-learnTrajs=152025.02 | 95.34 | 26.92 | |
| BCTrajs=152025.02 | 95.33 | 15.42 |