From 26af688d4d03989e4f69e5fe7b49f3673b8d7072 Mon Sep 17 00:00:00 2001
From: Daniel Rosel <daniel@alves.world>
Date: Fri, 7 Nov 2025 14:33:46 +0100
Subject: [PATCH] algorithms and acknowledgements

---
 paper/src/chapters/03-methodology.tex   | 12 ++++++++++++
 paper/src/chapters/acknowledgements.tex |  3 +++
 paper/src/preamble.tex                  |  1 +
 3 files changed, 16 insertions(+)
 create mode 100644 paper/src/chapters/acknowledgements.tex

diff --git a/paper/src/chapters/03-methodology.tex b/paper/src/chapters/03-methodology.tex
index 2c13011..dd21186 100644
--- a/paper/src/chapters/03-methodology.tex
+++ b/paper/src/chapters/03-methodology.tex
@@ -54,3 +54,15 @@ Deep dive into how the algorithm works, different kinds and justification for ch
 \subsection{Reinforcement Learning Formulation}
 How do we define the state space, action space and reward function breakdown and algorithm benchmarking.
 POSSIBLY: Expand into full subsections: 3.6.1 (State-Action Space), 3.6.2 (Reward Design), 3.6.3 (Benchmarking)
+
+
+\begin{algorithm}[t]
+\DontPrintSemicolon
+\KwIn{stepsize $\eta$, smoothing $\delta$, rank $d$}
+\For{$t=1$ \KwTo $T$}{
+  Sample $u_t$ on unit sphere; set $x_t^\prime=x_t+\delta u_t$\;
+  Set $p_t \gets U x_t^\prime$ and observe $q_t, R_t(p_t)$\;
+  $x_{t+1} \gets \Pi\_{\mathcal{X}}(x_t-\eta R_t(p_t) u_t)$\;
+}
+\caption{Online Pricing Optimization (template)}
+\end{algorithm}
diff --git a/paper/src/chapters/acknowledgements.tex b/paper/src/chapters/acknowledgements.tex
new file mode 100644
index 0000000..160bad2
--- /dev/null
+++ b/paper/src/chapters/acknowledgements.tex
@@ -0,0 +1,3 @@
+\section{Acknowledgements}
+
+Eugene Bykovets, PhD - ETH
diff --git a/paper/src/preamble.tex b/paper/src/preamble.tex
index 91cd761..0acd7c7 100644
--- a/paper/src/preamble.tex
+++ b/paper/src/preamble.tex
@@ -7,6 +7,7 @@
 \usepackage{tikz}
 \usepackage{listings}
 \usepackage{xcolor}
+\usepackage[ruled,vlined]{algorithm2e}
 
 \usetikzlibrary{positioning, shapes, arrows.meta, fit, backgrounds}
 \lstset{