Continuous Control (Negative Reward) on Reacher Pybullet
16.8Mean ReturnImplementation [20]
Evaluation Results
| Method | Links | |
|---|---|---|
| Implementation [20]strategy=underest2023.08 | 16.8 | |
| Implementation [20]strategy=ignore2023.08 | 15.3 | |
| Implementation [21]strategy=ignore2023.08 | 4.1 | |
| Implementation [21]strategy=underest2023.08 | 3.5 | |
| Implementation [20]strategy=zero2023.08 | 1.5 | |
| Implementation [21]strategy=zero2023.08 | -11.8 |