常用LaTex語法
常用LaTex語法
符號
點 | \(\cdot\) | \(\cdots\) | \(\vdots\) | \(\ddots\) |
---|---|---|---|---|
LaTex | \cdot | \cdots | \vdots | \ddots |
等號/箭頭 | \(\approx\) | \(\sim\) | \(\propto\) | \(\geq\) | \(\leq\) | \(\Rightarrow\) | \(\Longrightarrow\) | \(\rightrightarrows\) | \(\rightleftarrows\) |
---|---|---|---|---|---|---|---|---|---|
LaTex | \approx | \sim | \propto | \geq | \leq | \Rightarrow | \Longrightarrow | \rightrightarrows | \rightleftarrows |
運算子 | \(\prod\) | \(\sum\) | \(\int\) | \(\partial x\) | \(\nabla\) | \(\in\) | \(\not\in\) | \(\subset\) | \(\not\subset\) | \(a \cdot b\) | \(a \times b\) | \(a \div b\) |
---|---|---|---|---|---|---|---|---|---|---|---|---|
LaTex | \prod | \sum | \int | \partial x | \nabla | \in | \not\in | \subset | \not\subset | a \cdot b | a \times b | a \div b |
上/下劃線 | \(\widetilde x\) | \(\overline{\text{x}}\) | \(\widetilde x\) | \(\tilde x\) | \(\underline{V}_{n}\) | \(\overline V_n\) |
---|---|---|---|---|---|---|
LaTex | \widetilde x | \overline{\text{x}} | \widetilde x | \tilde x | \underline{V}_{n} | \overline{V}_n |
絕對值/取整 | \(\vert\) | \(\Vert\) | \(\lfloor\) | \(\rfloor\) | \(\lceil\) | \(\rceil\) |
---|---|---|---|---|---|---|
LaTex | \vert | \Vert | \lfloor | \rfloor | \lceil | \rceil |
字母
字母 | \(\mathbb{T}\) | \(\mathcal{T}\) | \(\mathscr{T}\) | \(\mathsf{T}\) | \(\mathtt{T}\) | \(\mathit{T}\) |
---|---|---|---|---|---|---|
LaTex | \mathbb{T} | \mathcal{T} | \mathscr{T} | \mathsf{T} | \mathtt{T} | \mathit{T} |
公式
\[\pi^*(a|s)= \left\{\begin{array}{l} 1,if \quad a=\arg\max\limits_{a \in A}q^*(s,a)\\ 0,otherwise \end{array}\right. \]
$$
\pi^*(a|s)=
\left\{\begin{array}{l}
1,if \quad a=\arg\max\limits_{a \in A}q^*(s,a)\\
0,otherwise
\end{array}\right.
$$
\[T=\begin{pmatrix} 0 & 0 & 1 & \frac{1}{2} \\ \frac{1}{3} & 0 & 0 & 0 \\ \frac{1}{3} & \frac{1}{2} & 0 & \frac{1}{2} \\ \frac{1}{3} & \frac{1}{2} & 0 & 0 \end{pmatrix} \]
$$
T=\begin{pmatrix}
0 & 0 & 1 & \frac{1}{2} \\
\frac{1}{3} & 0 & 0 & 0 \\
\frac{1}{3} & \frac{1}{2} & 0 & \frac{1}{2} \\
\frac{1}{3} & \frac{1}{2} & 0 & 0
\end{pmatrix}
$$
\[\begin{array}{l} q_\pi(s,a) \overset{.}{=} E_\pi[G_t|S_t=s,A_t=a] \\ \qquad \quad \ = E_\pi[R_{t+1}+\gamma G_{t+1}|S_t=s,A_t=a] \\ \qquad \quad \ = \sum_{s^\prime,r}p(s^\prime,r|s,a)[r+\gamma \sum_{a^\prime}\pi(a^\prime|s^\prime)E_\pi[G_{t+1}|S_{t+1}=s^\prime,A_{t+1}=a^\prime]] \\ \qquad \quad \ = \sum_{s^\prime,r}p(s^\prime,r|s,a)[r+\gamma \sum_{a^\prime}\pi(a^\prime|s^\prime)q_\pi(s^\prime,a^\prime) \end{array} \\ \]
$$
\begin{array}{l}
q_\pi(s,a) \overset{.}{=} E_\pi[G_t|S_t=s,A_t=a] \\
\qquad \quad \ = E_\pi[R_{t+1}+\gamma G_{t+1}|S_t=s,A_t=a] \\
\qquad \quad \ = \sum_{s^\prime,r}p(s^\prime,r|s,a)[r+\gamma \sum_{a^\prime}\pi(a^\prime|s^\prime)E_\pi[G_{t+1}|S_{t+1}=s^\prime,A_{t+1}=a^\prime]] \\
\qquad \quad \ = \sum_{s^\prime,r}p(s^\prime,r|s,a)[r+\gamma \sum_{a^\prime}\pi(a^\prime|s^\prime)q_\pi(s^\prime,a^\prime)
\end{array}
\\
$$