Reinforcement Learning on 3D Quadrotor
-0.63Episode ReturnRay Mask
Evaluation results
| Method | Links | |
|---|---|---|
| Ray MaskMasking Strategy=Ray Masking2024.06 | -0.63 | |
| Distributional MaskMasking Strategy=Distributional Masking2024.06 | -0.66 | |
| ReplacementMasking Strategy=Action Replacement2024.06 | -0.68 | |
| Generator MaskMasking Strategy=Generator Masking2024.06 | -0.68 | |
| BaselineMasking Strategy=None2024.06 | -1 |