velocitatem/PHANTOM
1
0
Fork 0
mirror of https://github.com/velocitatem/PHANTOM.git synced 2026-05-31 16:43:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

algorithms and acknowledgements

Browse Source
This commit is contained in:
Daniel Rosel
2025-11-07 14:33:46 +01:00
parent 8174cd3ef5
commit 26af688d4d
3 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
paper/src/chapters/03-methodology.tex
View File

@@ -54,3 +54,15 @@ Deep dive into how the algorithm works, different kinds and justification for ch
\subsection{Reinforcement Learning Formulation} \subsection{Reinforcement Learning Formulation}
How do we define the state space, action space and reward function breakdown and algorithm benchmarking. 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) 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}

3
paper/src/chapters/acknowledgements.tex Normal file
View File

@@ -0,0 +1,3 @@
\section{Acknowledgements}
Eugene Bykovets, PhD - ETH

1
paper/src/preamble.tex
View File

@@ -7,6 +7,7 @@
\usepackage{tikz} \usepackage{tikz}
\usepackage{listings} \usepackage{listings}
\usepackage{xcolor} \usepackage{xcolor}
\usepackage[ruled,vlined]{algorithm2e}
\usetikzlibrary{positioning, shapes, arrows.meta, fit, backgrounds} \usetikzlibrary{positioning, shapes, arrows.meta, fit, backgrounds}
\lstset{ \lstset{