Update README.md

README.md

@@ -11,9 +11,7 @@ We introduce **ActAIM2**, which given an RGBD image of an articulated object and
 
 ## Problem Formulation
 
-
-  $$\mathbb{P}(a|o) = \int \underbrace{\mathbb{P}(a|o,\epsilon)}_{\text{action predictor}}~  \underbrace{\mathbb{P}(\epsilon|o)}_{\text{mode selector}} d\epsilon $$
-
+Our model training aims to uncover the policy's distribution $\mathbb{P}(a|o)$, with $o$ representing the observation and $a=(\mathbf{p}, \mathbf{R}, \mathbf{q})$ the action, through a decomposition strategy that reconfigures the action distribution as: