https://datafranca.org/wiki/index.php?action=history&feed=atom&title=Th%C3%A9or%C3%A8me_du_gradient_de_politique 2026-04-25T10:21:19Z Historique des versions pour cette page sur le wiki MediaWiki 1.39.5 https://datafranca.org/wiki/index.php?title=Th%C3%A9or%C3%A8me_du_gradient_de_politique&diff=112586&oldid=prev 2025-04-28T14:02:29Z

<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 28 avril 2025 à 10:02</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l15">Ligne 15 :</td> <td colspan="2" class="diff-lineno">Ligne 15 :</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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem  Lilian Weng Blog - Policy Gradient Theorem]</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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem  Lilian Weng Blog - Policy Gradient Theorem]</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" 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;">Categorie</del>:GRAND LEXIQUE FRANÇAIS<del style="font-weight: bold; text-decoration: none;">]]</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;">Catégorie</ins>:GRAND LEXIQUE FRANÇAIS]]</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;">[[Catégorie:Publication</del>]]</div></td><td colspan="2" class="diff-side-added"></td></tr> </table>

Pitpitt https://datafranca.org/wiki/index.php?title=Th%C3%A9or%C3%A8me_du_gradient_de_politique&diff=112584&oldid=prev 2025-04-28T14:01:08Z

<p>Pitpitt a déplacé la page <a href="/wiki/Policy_Gradient_Theorem" class="mw-redirect" title="Policy Gradient Theorem">Policy Gradient Theorem</a> vers <a href="/wiki/Th%C3%A9or%C3%A8me_du_gradient_de_politique" title="Théorème du gradient de politique">Théorème du gradient de politique</a></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <tr class="diff-title" lang="fr"> <td colspan="1" style="background-color: #fff; color: #202122; text-align: center;">← Version précédente</td> <td colspan="1" style="background-color: #fff; color: #202122; text-align: center;">Version du 28 avril 2025 à 10:01</td> </tr><tr><td colspan="2" class="diff-notice" lang="fr"><div class="mw-diff-empty">(Aucune différence)</div> </td></tr></table>

Pitpitt https://datafranca.org/wiki/index.php?title=Th%C3%A9or%C3%A8me_du_gradient_de_politique&diff=112282&oldid=prev 2025-04-25T07:55:19Z

<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 25 avril 2025 à 03:55</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l13">Ligne 13 :</td> <td colspan="2" class="diff-lineno">Ligne 13 :</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>==Sources==</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>==Sources==</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" 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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem <del style="font-weight: bold; text-decoration: none;">- </del>Lilian Weng Blog<del style="font-weight: bold; text-decoration: none;">, Proof of </del>Policy Gradient Theorem]</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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem <ins style="font-weight: bold; text-decoration: none;"> </ins>Lilian Weng Blog <ins style="font-weight: bold; text-decoration: none;">- </ins>Policy Gradient Theorem]</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>[[Categorie:GRAND LEXIQUE 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>[[Categorie:GRAND LEXIQUE 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>[[Catégorie:Publication]]</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>[[Catégorie:Publication]]</div></td></tr> </table>

Claude COULOMBE https://datafranca.org/wiki/index.php?title=Th%C3%A9or%C3%A8me_du_gradient_de_politique&diff=112281&oldid=prev 2025-04-25T07:54:52Z

<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 25 avril 2025 à 03:54</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l13">Ligne 13 :</td> <td colspan="2" class="diff-lineno">Ligne 13 :</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>==Sources==</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>==Sources==</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" 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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem - Proof of Policy Gradient Theorem]</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>[https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem - <ins style="font-weight: bold; text-decoration: none;">Lilian Weng Blog, </ins>Proof of Policy Gradient Theorem]</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>[[Categorie:GRAND LEXIQUE 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>[[Categorie:GRAND LEXIQUE 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>[[Catégorie:Publication]]</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>[[Catégorie:Publication]]</div></td></tr> </table>

Claude COULOMBE https://datafranca.org/wiki/index.php?title=Th%C3%A9or%C3%A8me_du_gradient_de_politique&diff=112280&oldid=prev 2025-04-25T07:53:50Z

<p>Page créée avec « ==Définition== En <a href="/wiki/Apprentissage_par_renforcement" title="Apprentissage par renforcement">apprentissage par renforcement</a>, le théorème du gradient de politique permet de simplifier l&#039;apprentissage d&#039;une [politique d&#039;action] en établissant que le gradient (ou dérivée) de la récompense attendue en suivant une [politique d&#039;action] est l&#039;espérance du produit de la récompense attendue par le gradient (ou dérivée) du logarithme de la [politique d&#039;action]. La [politique d&#039;action] est généralement exprimée sous la forme d&#039;u... »</p> <p><b>Nouvelle page</b></p><div>==Définition==<br /> <br /> En [[apprentissage par renforcement]], le théorème du gradient de politique permet de simplifier l&#039;apprentissage d&#039;une [politique d&#039;action] en établissant que le gradient (ou dérivée) de la récompense attendue en suivant une [politique d&#039;action] est l&#039;espérance du produit de la récompense attendue par le gradient (ou dérivée) du logarithme de la [politique d&#039;action]. La [politique d&#039;action] est généralement exprimée sous la forme d&#039;une [[distribution de probabilité]].<br /> <br /> ==Français==<br /> <br /> &#039;&#039;&#039;théorème du gradient de politique&#039;&#039;&#039;<br /> <br /> ==Anglais==<br /> <br /> &#039;&#039;&#039;policy gradient theorem&#039;&#039;&#039;<br /> <br /> ==Sources==<br /> <br /> [https://lilianweng.github.io/posts/2018-04-08-policy-gradient/#proof-of-policy-gradient-theorem - Proof of Policy Gradient Theorem]<br /> <br /> [[Categorie:GRAND LEXIQUE FRANÇAIS]]<br /> [[Catégorie:Publication]]</div>

Claude COULOMBE