Continuous Control (Negative Reward) on Reacher Mujoco
-6.3Mean ReturnImplementation [21]
Evaluation Results
| Method | Links | |
|---|---|---|
| Implementation [21]strategy=zero2023.08 | -6.3 | |
| Implementation [20]strategy=ignore2023.08 | -7.3 | |
| Implementation [21]strategy=ignore2023.08 | -7.3 | |
| Implementation [21]strategy=underest2023.08 | -8 | |
| Implementation [20]strategy=zero2023.08 | -8.6 | |
| Implementation [20]strategy=underest2023.08 | -11.4 |