Continuous Control (Negative Reward) on Pendulum Pybullet
9,124.6Mean ReturnImplementation [21]
Evaluation Results
| Method | Links | |
|---|---|---|
| Implementation [21]strategy=underest2023.08 | 9,124.6 | |
| Implementation [20]strategy=underest2023.08 | 6,629.6 | |
| Implementation [21]strategy=ignore2023.08 | 6,256.1 | |
| Implementation [20]strategy=ignore2023.08 | 1,117 | |
| Implementation [20]strategy=zero2023.08 | 140.5 | |
| Implementation [21]strategy=zero2023.08 | 139.7 |