https://datafranca.org/wiki/index.php?action=history&feed=atom&title=DAPO
DAPO - Historique des versions
2026-04-10T23:54:06Z
Historique des versions pour cette page sur le wiki
MediaWiki 1.39.5
https://datafranca.org/wiki/index.php?title=DAPO&diff=118596&oldid=prev
Arianne le 4 mars 2026 à 16:45
2026-03-04T16:45:33Z
<p></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="fr">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Version précédente</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Version du 4 mars 2026 à 12:45</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l2">Ligne 2 :</td>
<td colspan="2" class="diff-lineno">Ligne 2 :</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Définition ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Définition ==</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">xxxxxxx</del></div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">'''[[Algorithme]]''' d''''[[apprentissage par renforcement]]''' qui solidifie les schémas de raisonnement et qui donne également naissance à de nouveaux modes de raisonnement facilitant une ''bonne'' résolution des problèmes. L'un de ses avantages est qu'il n'affecte pas de manière significative la durée totale de l''''[[entraînement]]'''.</ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div> </div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Voir aussi '''[[optimisation de la politique proximale]]''' et '''[[optimisation de la politique relative au groupe]]'''</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Français ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Français ==</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>''' XXXXXXXX'''</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>''' XXXXXXXX'''</div></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;"></del></div></td><td colspan="2" class="diff-side-added"></td></tr>
<tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">Voir aussi '''[[optimisation de la politique proximale]]''' et '''[[optimisation de la politique relative au groupe]]'''</del></div></td><td colspan="2" class="diff-side-added"></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Anglais ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Anglais ==</div></td></tr>
</table>
Arianne
https://datafranca.org/wiki/index.php?title=DAPO&diff=118460&oldid=prev
Arianne : Page créée avec « == en construction == == Définition == xxxxxxx == Français == ''' XXXXXXXX''' Voir aussi '''optimisation de la politique proximale''' et '''optimisation de la politique relative au groupe''' == Anglais == ''' DAPO''' ''' Decoupled Clip and Dynamic Sampling Policy Optimization''' <!--A reinforcement learning algorithm that reinforces reasoning patterns and also gives rise to new modes of reasoning that facilitate correct problem-solving. One of its... »
2026-02-22T20:03:53Z
<p>Page créée avec « == en construction == == Définition == xxxxxxx == Français == ''' XXXXXXXX''' Voir aussi '''<a href="/wiki/Optimisation_de_la_politique_proximale" class="mw-redirect" title="Optimisation de la politique proximale">optimisation de la politique proximale</a>''' et '''<a href="/wiki/Optimisation_de_la_politique_relative_au_groupe" title="Optimisation de la politique relative au groupe">optimisation de la politique relative au groupe</a>''' == Anglais == ''' DAPO''' ''' Decoupled Clip and Dynamic Sampling Policy Optimization''' <!--A reinforcement learning algorithm that reinforces reasoning patterns and also gives rise to new modes of reasoning that facilitate correct problem-solving. One of its... »</p>
<p><b>Nouvelle page</b></p><div>== en construction ==<br />
<br />
== Définition ==<br />
xxxxxxx<br />
<br />
== Français ==<br />
''' XXXXXXXX'''<br />
<br />
Voir aussi '''[[optimisation de la politique proximale]]''' et '''[[optimisation de la politique relative au groupe]]'''<br />
<br />
== Anglais ==<br />
''' DAPO'''<br />
<br />
''' Decoupled Clip and Dynamic Sampling Policy Optimization'''<br />
<br />
<!--A reinforcement learning algorithm that reinforces reasoning patterns and also gives rise to new modes of reasoning that facilitate correct problem-solving. One of its advantages is that it does not significantly affect the overall training time.--><br />
<br />
== Sources ==<br />
[https://arxiv.org/abs/2503.14476 Source : arxiv]<br />
<br />
[https://dapo-sia.github.io/ Source : DAPO, GitHub]<br />
<br />
[https://verl.readthedocs.io/en/latest/algo/dapo.html Source : verl]<br />
<br />
[[Catégorie:vocabulary]]</div>
Arianne