Reinforcement Learning on 2D Quadrotor
-0.23Episode ReturnDistributional Mask
Evaluation results
| Method | Links | |
|---|---|---|
| Distributional MaskMasking Strategy=Distributional Masking2024.06 | -0.23 | |
| ReplacementMasking Strategy=Action Replacement2024.06 | -0.25 | |
| Generator MaskMasking Strategy=Generator Masking2024.06 | -0.25 | |
| Ray MaskMasking Strategy=Ray Masking2024.06 | -0.26 | |
| BaselineMasking Strategy=None2024.06 | -0.8 |