mirror of
https://github.com/velocitatem/PHANTOM.git
synced 2026-05-31 08:33:36 +00:00
a9d73ccce5
* initial environemnt definitions * high level defintion * formlating the reward simply * improved implementation * tailored docker compose image for secondary tenaordboard * preliminary desriptions and babble * details on formulation and defintion of agent and its loop * typos one * more grammar issues * fluidity improvements and refactors * more decluttering and dnoising * finalizing introduction review * some methodology * somehow this disappeared * bit more of this and that * methodology of how we do architectuer and online DP * fix: compilation * expanding on the taxonomy and economic references * authoer notes * acks + google GCP * making space w new format nada lit review * stronger lit review and more sources * forgot about tables and graphs * dedupe citations * adding cloudflare * fixing env vars * updating docs with url * upating embed * fixing the url * paper badge * formaliztaion of rewards and adding definitions * noisy formulations * connecting some more dots here * adding significant weight in prices * fixing error * fixing typos and consistency * extra math formulations and refferenceot DRO * fixing diagram of loops * github mindmap * fixing erro and thiknig about big picture * enhancing the website * goals methodology and gitignore * some more references and theory links * talking about some wtp * feature: added wordcounter * forcing latex builds and fixining the bib # * refactor: update Cost of Information equations and notation for clarity * some more math and refactors * refactor: unify notation and improve clarity in COI equations * refactor: generalize master function for demand estimation and pricing strategies * we dont like math but we have to do it :( * refactor: enhance Cost of Information framework with additional context and illustration * refactor: enhance literature review and methodology sections with economic theory insights and system architecture details * alining format to fit the rubric * refactoring bibliography * fix: align * mdp additionally * trying different title * adding balance figure * agentic givergence, finally * fix: figure fonts adjusted to match
111 lines
3.6 KiB
TeX
111 lines
3.6 KiB
TeX
\definecolor{mygreenfill}{RGB}{169, 234, 186}
|
|
\definecolor{mygreenborder}{RGB}{29, 145, 61}
|
|
\definecolor{mybluefill}{RGB}{204, 222, 255}
|
|
\definecolor{myblueborder}{RGB}{66, 106, 189}
|
|
\definecolor{mygray}{RGB}{150, 150, 150}
|
|
|
|
|
|
|
|
\begin{tikzpicture}[
|
|
node distance=2cm,
|
|
% Style for Green Nodes
|
|
greenbox/.style={
|
|
rectangle,
|
|
draw=mygreenborder,
|
|
fill=mygreenfill,
|
|
line width=1.2pt,
|
|
align=center,
|
|
minimum height=1cm
|
|
},
|
|
% Style for Blue Nodes
|
|
bluebox/.style={
|
|
rectangle,
|
|
draw=myblueborder,
|
|
fill=mybluefill,
|
|
line width=1.2pt,
|
|
align=center,
|
|
minimum height=1cm
|
|
},
|
|
% Style for Arrows
|
|
myarrow/.style={
|
|
->,
|
|
>={Stealth[length=3mm, width=2mm]},
|
|
draw=black!80,
|
|
line width=1.2pt,
|
|
rounded corners=5pt
|
|
},
|
|
% Style for Background Dashed Circles
|
|
dashedloop/.style={
|
|
dashed,
|
|
draw=mygray,
|
|
line width=1pt
|
|
}
|
|
]
|
|
|
|
% --- Coordinate Layout ---
|
|
% Defining a grid relative to the center
|
|
|
|
% Left Loop (Green) Nodes
|
|
\node[greenbox, minimum width=3.5cm] (commerce) at (-3.5, 2) {Commerce Experiment};
|
|
\node[greenbox, minimum width=1.5cm] (raw) at (-6.5, 0) {Raw\\Logs};
|
|
\node[greenbox, minimum width=1.5cm] (features) at (-4, -2.5) {Features};
|
|
\node[greenbox, minimum width=2.5cm] (classification) at (-1, -0.5) {Classification\\Training A/H};
|
|
|
|
% Right Loop (Blue) Nodes
|
|
\node[bluebox, minimum width=2.5cm] (trainedpricing) at (3.2, 2) {Trained Pricing};
|
|
\node[bluebox, minimum width=2.5cm] (policy) at (6.5, 0) {Trained Pricing\\Policy};
|
|
\node[bluebox, minimum width=2.5cm] (rlgym) at (3.2, -2.2) {RL Gym\\Training};
|
|
|
|
% --- Background Dashed Loops ---
|
|
\begin{scope}[on background layer]
|
|
% Left Loop Circle
|
|
\draw[dashedloop] (-3.5, 0) ellipse (3.5cm and 2.8cm);
|
|
% Right Loop Circle
|
|
\draw[dashedloop] (3.5, 0) ellipse (3.5cm and 2.8cm);
|
|
\end{scope}
|
|
|
|
% --- Arrows: Loop One (Green) ---
|
|
% Commerce -> Raw Logs
|
|
\draw[myarrow] (commerce.west) to[out=180, in=90] (raw.north);
|
|
|
|
% Raw Logs -> Features
|
|
\draw[myarrow] (raw.south) to[out=270, in=180] (features.west);
|
|
|
|
% Features -> Classification
|
|
\draw[myarrow] (features.east) to[out=0, in=250] (classification.south);
|
|
|
|
% Classification -> Commerce (Closing the loop)
|
|
\draw[myarrow] (classification.north) to[out=110, in=0] (commerce.east);
|
|
|
|
% --- Arrows: Loop Two (Blue) ---
|
|
% Classification (Green) -> RL Gym (Blue) - Crossing over
|
|
\draw[myarrow] (classification.east) to[out=0, in=180] (rlgym.west);
|
|
|
|
% RL Gym -> Policy
|
|
\draw[myarrow] (rlgym.east) to[out=0, in=270] (policy.south);
|
|
|
|
% Policy -> Trained Pricing
|
|
\draw[myarrow] (policy.north) to[out=90, in=0] (trainedpricing.east);
|
|
|
|
% Trained Pricing -> Commerce (Crossing back)
|
|
\draw[myarrow] (trainedpricing.west) -- node[above, font=\small, yshift=2pt] {New Pricing} (commerce.east);
|
|
|
|
% --- Text Labels ---
|
|
|
|
% Loop One Label
|
|
\node[align=center] at (-3.8, 0) {Loop One:\\Data \textit{(Online)}};
|
|
|
|
% Loop Two Label
|
|
\node[align=center] at (3.5, 0) {Loop Two:\\Defense Gym \textit{(Offline)}};
|
|
|
|
% Bottom Legend
|
|
\node[font=\small] (taskA) at (-4, -4) {Dynamic Pricing Task A};
|
|
\node[font=\small] (taskB) at (4, -4) {Dynamic Pricing Task B};
|
|
\node[font=\small] (indep) at (0, -4) {Independent};
|
|
|
|
% Arrows for bottom legend
|
|
\draw[->, >=Stealth, thick, darkgray] (indep.west) -- (taskA.east);
|
|
\draw[->, >=Stealth, thick, darkgray] (indep.east) -- (taskB.west);
|
|
|
|
\end{tikzpicture}
|