update.

section7/section7.tex

@@ -163,3 +163,4 @@ Based on these estimated advantages, we formulate the GRPO objective as follows:
 \mathrm{clip}(\frac{\mathrm{Pr}_\theta(a_t^i|s_t^i)}{\mathrm{Pr}_{\theta_{\mathrm{old}}}(a_t^i|s_t^i)},1-\epsilon,1+\epsilon)\hat{A}_i)\right]
 \mathrm{clip}(\frac{\mathrm{Pr}_\theta(a_t^i|s_t^i)}{\mathrm{Pr}_{\theta_{\mathrm{old}}}(a_t^i|s_t^i)},1-\epsilon,1+\epsilon)\hat{A}_i)\right]
 \end{eqnarray}
 \end{eqnarray}
 
 
+During training, one challenge is trajectory sampling 
\ No newline at end of file