Created
March 12, 2021 14:22
-
-
Save daanklijn/4e16aa928890b7cae37a39dbce5c71b9 to your computer and use it in GitHub Desktop.
Multi-agent Reinforcement Learning flowchart using LaTeX and TikZ
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
\begin{tikzpicture}[node distance = 6em, auto, thick] | |
\node [block] (Agent1) {Agent$_1$}; | |
\node [block, below of=Agent1] (Agent2) {Agent$_2$}; | |
\node [below of=Agent2] (Dots) {\cvdots}; | |
\node [block, below of=Dots] (Agent3) {Agent$_n$}; | |
\node [block, below of=Agent3] (Environment) {Environment}; | |
\path [line] (Agent1.0) --++ (10em,0em) |- node [near start]{$a_{1,t}$} (Environment.-15); | |
\path [line] (Agent2.0) --++ (6em,0em) |- node [near start]{$a_{2,t}$} (Environment.0); | |
\path [line] (Agent3.0) --++ (2em,0em) |- node [near start]{$a_{n,t}$} (Environment.15); | |
\path [line] (Environment.195) --++ (-18em,0em) |- node [near start] {$s_{1,t+1}, r_{1,t+1}$} (Agent1.180); | |
\path [line] (Environment.180) --++ (-10em,0em) |- node [near start] {$s_{2,t+1}, r_{2,t+1}$} (Agent2.180); | |
\path [line] (Environment.165) --++ (-2em,0em) |- node [near start] {$s_{n,t+1}, r_{n,t+1}$} (Agent3.180); | |
\end{tikzpicture} |
Author
daanklijn
commented
Mar 12, 2021
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment