Skip to content

Commit

Permalink
Add pseudocode and some more content skeleton
Browse files Browse the repository at this point in the history
  • Loading branch information
abhaybd authored and Abhay Deshpande committed Apr 13, 2024
1 parent 1a0201d commit c5b154c
Show file tree
Hide file tree
Showing 2 changed files with 69 additions and 4 deletions.
66 changes: 63 additions & 3 deletions index.html
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,17 @@
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning</title>

<script>
MathJax = {
tex: {
inlineMath: [['$','$'], ['\\(','\\)']],
displayMath: [['$$','$$'], ['\\[','\\]']],
processEscapes: true,
processEnvironments: true,
}
}
</script>

<link href="https://fonts.googleapis.com/css?family=Google+Sans|Noto+Sans|Castoro" rel="stylesheet">

<link rel="stylesheet" href="./static/css/bulma.min.css">
Expand All @@ -16,8 +27,13 @@
<link rel="stylesheet" href="./static/css/fontawesome.all.min.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/gh/jpswalsh/academicons@1/css/academicons.min.css">
<link rel="stylesheet" href="./static/css/index.css">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/pseudocode@latest/build/pseudocode.min.css">
<link rel="icon" href="./static/images/favicon.svg" type="image/svg">

<script src="https://cdn.jsdelivr.net/npm/[email protected]/es5/tex-chtml-full.js"
integrity="sha256-kbAFUDxdHwlYv01zraGjvjNZayxKtdoiJ38bDTFJtaQ="
crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/npm/pseudocode@latest/build/pseudocode.min.js"></script>
<script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
<script defer src="./static/js/fontawesome.all.min.js"></script>
<script src="./static/js/bulma-carousel.min.js"></script>
Expand Down Expand Up @@ -171,7 +187,7 @@ <h3 class="title publication-title">Data Efficient Behavior Cloning for Fine Man
<div class="container is-max-desktop">
<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">The Problem</h2>
<h2 class="title is-2">The Problem</h2>
<div class="content has-text-justified">
<p>
Imitation learning in robotics demands extensive data coverage, often necessitating
Expand All @@ -193,9 +209,11 @@ <h2 class="title is-3">The Problem</h2>

<div class="columns is-centered has-text-centered">
<div class="column is-four-fifths">
<h2 class="title is-3">CCIL</h2>
<h2 class="title is-2">CCIL</h2>
<div class="content has-text-centered">
<img src="./static/images/ccil_overview.png" alt="CCIL Overview" style="max-width: 90%;"/>
</div>
<div class="content has-text-justified">
<img src="./static/images/ccil_overview.png" alt="CCIL Overview" />
<p>
Our approach focuses on synthesizing corrective labels to guide an agent encountering unfamiliar states
back to the distribution of expert states, ensuring safety and familiarity. Leveraging local continuity in
Expand All @@ -209,6 +227,45 @@ <h2 class="title is-3">CCIL</h2>
through extensive simulation experiments, as well as in fine manipulation on a real robotic platform.
</p>
</div>
<div class="content has-text-justified">
<pre class="pseudocode">
\begin{algorithm}
\caption{Our Instantiation of CCIL: \textbf{C}ontinuity-based \textbf{C}orrective labels for \textbf{I}mitation \textbf{L}earning}
\begin{algorithmic}
\STATE \textbf{Input:} $\mathcal{D^*}=(s^*_i, a^*_i, s^*_{i+1})$
\STATE \textbf{Initialize:} $D^\mathcal{G} \leftarrow \varnothing$
\STATE \texttt{// Learn Dynamics}
\STATE $MSE\leftarrow\mathbb{E}_{(s^*_i,a^*_i,s^*_{i+1})\sim \mathcal{D}^*}\left[\hat{f}(s^*_i, a^*_i) + s^*_i - s^*_{i+1}\right]$
\STATE $\hat{f}\leftarrow\arg\min_{\hat{f}} MSE \mkern9mu\text{s.t.}\mkern9mu \|W\|_2\leq L$
\STATE \texttt{// Generate Labels}
\FOR{$i=1 .. n$}
\STATE $(s^\mathcal{G}_i, a^\mathcal{G}_i) \leftarrow$ \CALL{GenLabels}{$s^*_i, a^*_i, s^*_\text{i+1}$}
\IF{$||J_{\hat{f}}(s^*_i, a^*_i)||_2\cdot||s^\mathcal{G}_i - s^*_i || < \epsilon$}
\STATE $\mathcal{D^G} \leftarrow \mathcal{D^G} \cup (s^\mathcal{G}_i, a^\mathcal{G}_i)$
\ENDIF
\ENDFOR
\STATE $\mathcal{D}\leftarrow\mathcal{D}^* \cup \mathcal{D}^\mathcal{G}$
\STATE \texttt{// Learn Policy}
\STATE $\pi \leftarrow$ \CALL{LearnPolicy}{}
\PROCEDURE{GenLabels}{$s^*_i, a^*_i, s^*_\text{i+1}$}
\STATE $a^\mathcal{G}_i \leftarrow a^*_i$
\STATE $s^\mathcal{G}_i \leftarrow s^*_i - \hat{f}(s^*_i,a^*_i)$
\ENDPROCEDURE
\PROCEDURE{LearnPolicy}{}
\STATE $L(a,\hat{a})\leftarrow$ policy loss function (see paper)
\STATE $\pi=\arg\min_{\pi}\mathbb{E}_{(s_i,a_i)\sim\mathcal{D}}\left[L(a_i, \pi(s_i))\right]$
\ENDPROCEDURE
\end{algorithmic}
\end{algorithm}
</pre>
</div>
<h3 class="title is-3">Label Generation</h3>
<div class="content has-text-justified">
<p>
We do cool stuff to generate labels.
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
</p>
</div>
</div>
</div>

Expand Down Expand Up @@ -545,6 +602,9 @@ <h2 class="title">BibTeX</h2>
</div>
</footer>

<script>
pseudocode.renderClass("pseudocode");
</script>
</body>

</html>
7 changes: 6 additions & 1 deletion static/css/index.css
Original file line number Diff line number Diff line change
Expand Up @@ -199,4 +199,9 @@ body {

.inside-hypothesis {
padding: 0 50px;
}
}

/* Formatting for pseudocode.js */
.ps-root p.ps-line {
margin: 0;
}

0 comments on commit c5b154c

Please sign in to comment.