latex.md

Written by KimRass

Number of Prameters: 0

{\cdot}

\infty

\in

\ne

\le, \ge

\forall

\leftarrow, \rightarrow, \leftrightarrow

\sim

\overset{\underset{\mathrm{def}}{}}{=}

Number of Prameters: 1

\mathbb{}

\mathbb{E}

\vec{}

\hat{}

\left, \right

\big, \bigg, \Big, \Bigg

\begin{} \end{}

\begin{array} \end{array}

\pi^{*}(a|s)=\left\{
\begin{array}{c l}	
    1, & if\ a = \underset{a \in A}{\operatorname{argmax}}Q^{*}(s, a)\\
    0, & otherwise
\end{array}\right.

\begin{align} \end{align}

$$\pi(a|s) =
\left\{
\begin{align}
&\frac{\epsilon}{|A|} + 1 - \epsilon
&&if\ a = \underset{a \in A}{\operatorname{argmax}}Q^{\pi}(s, a)\\
&\frac{\epsilon}{|A|}
&&otherwise
\end{align}
\right.$$

$$\begin{align} \mathbb{E}{x \sim P}[f(x)] &= \sum{x \in X}p(x)f(x)\ &= \sum_{x \in X}q(x)\frac{p(x)}{q(x)}f(x)\ &= \mathbb{E}{x \sim Q}\left[\frac{p(x)}{q(x)}f(x)\right] \end{align}$$ $$\prod{k=t}^{T-1}\frac{\pi(A_{k}|S_{k})}{\mu(A_{k}|S_{k})}$$

Number of Prameters: 2

\sum_{}^{}

\prod_{}^{}

\frac{}{}

\frac{1}{2}

\underset{}{\operatorname{}}

\underset{a \in A}{\operatorname{argmax}}