提交 0c0140f8 编写于 作者: X xiaowei_xing

test

上级 775ef939
......@@ -272,4 +272,12 @@ $$
$$
\nabla_{\theta} V(\theta) = \mathbb{E}_ {\pi_{\theta}}[r_0 \nabla_{\theta} \log\pi_{\theta}(a_0|s_0) +
$$
$$
r_1(\nabla_{\theta} \log\pi_{\theta}(a_0|s_0) + \nabla_{\theta} \log\pi_{\theta}(a_1|s_1)) +
$$
$$
r_2(\nabla_{\theta} \log\pi_{\theta}(a_0|s_0) + \nabla_{\theta} \log\pi_{\theta}(a_1|s_1) + \nabla_{\theta} \log\pi_{\theta}(a_2|s_2))]
$$
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册