test

docs/8&9.md

@@ -391,4 +391,8 @@ $$
 
 $$
 = \mathbb{E}_ {s_{0:t},a_{0:(t-1)}}[b(s_t)\mathbb{E}_ {a_t}[\nabla_{\theta} \log \pi_{\theta}(a_t|s_t)]] \quad \text{（移除无关变量）}
+$$
+
+$$
+= \mathbb{E}_ {s_{0:t},a_{0:(t-1)}}[b(s_t) \sum_a \pi_{\theta}(a_t|s_t)\frac{\nabla_{\theta}\pi_{\theta}(a_t|s_t)}{\pi_{\theta}(a_t|s_t)}] \quad \text{（将期望展开 + test对数函数求导）}
 $$
\ No newline at end of file