[{"command":"insert","method":null,"selector":".course-modal-ajax-placeholder-956173","data":"\u003Cdiv class=\u0022container content-rte\u0022\u003E\n  \u003Cdiv class=\u0022row\u0022\u003E\n    \u003Cdiv class=\u0022box col-md-6 bg-primary text-white\u0022\u003E\n      \u003Ch2 class=\u0022h1 text-left\u0022\u003E  Reinforcement learning and approximation algorithms\n\u003C\/h2\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EECTS :\n          2.5\n        \u003C\/div\u003E\n      \u003C\/div\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ESemester:\n          Semestre 1\n        \u003C\/div\u003E\n      \u003C\/div\u003E\n            \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ED\u00e9tail du volume horaire\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003ELecture:\u003C\/span\u003E\n                                      \u003Cspan\u003E18\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                                                                        \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ELangue d\u0026#039;enseignement\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003EAnglais\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EEnseignement \u00e0 distance\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003Enon\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n      \u003C\/div\u003E\n    \u003Cdiv class=\u0022box col-md-6\u0022\u003E\n            \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EPr\u00e9requis\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EConnaissance du langage Python, notion de probabilit\u00e9s.\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EProgramme \/ plan \/ contenus\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EIntroduction \u00e0 l\u0027apprentissage par renforcement\u003C\/p\u003E\n\u003Cul\u003E\n\u003Cli\u003EQu\u2019est-ce que le RL ?\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EProcessus de d\u00e9cision markoviens (MDP)\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EConcepts de programmation dynamique\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003E\u00c9valuation et am\u00e9lioration de politiques\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EIt\u00e9ration de politique\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EIt\u00e9ration de valeur\u003C\/li\u003E\n\u003C\/ul\u003E\n\u003Cp\u003EM\u00e9thodes tabul\u00e9es\u003C\/p\u003E\n\u003Cul\u003E\n\u003Cli\u003E\u0026nbsp;M\u00e9thodes Monte Carlo\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003E\u0026nbsp;Apprentissage par diff\u00e9rence temporelle (TD)\u003C\/li\u003E\n\u003C\/ul\u003E\n\u003Cp\u003EApproximation de fonctions\u0026nbsp;\u003C\/p\u003E\n\u003Cul\u003E\n\u003Cli\u003EApproximation lin\u00e9aire\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EM\u00e9thodes de descente de gradient\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EM\u00e9thodes de gradient de politique\u0026nbsp;\u003C\/li\u003E\n\u003Cli\u003EAlgorithme REINFORCE\u0026nbsp;et techniques de r\u00e9duction de la variance\u003C\/li\u003E\n\u003C\/ul\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EObjectifs d\u0026#039;apprentissage\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003ELa partie RL du\u0026nbsp;\u0026nbsp;cours fournit une introduction approfondie \u00e0 l\u0027apprentissage par renforcement (RL), en mettant l\u0027accent sur les algorithmes fondamentaux et les applications pratiques. Les \u00e9tudiants aborderont les principes de la prise de d\u00e9cision s\u00e9quentielle, les bases des\u0026nbsp;\u0026nbsp;processus de d\u00e9cision markoviens, les fonctions de valeur, et l\u2019optimisation de politique.\u003C\/p\u003E\n\u003Cp\u003EDans toutes les s\u00e9ances, les \u00e9tudiants auront \u00e0 exp\u00e9rimenter les algorithmes et approches \u00e9tudi\u00e9s en instanciant des agents Python apprenant sur des probl\u00e8mes acad\u00e9miques.\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n                                \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EBibliographie\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003EReinforcement Learning: An Introduction, par Sutton \u0026amp; Barto\u003C\/p\u003E\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n        \u003Cdiv class=\u0022field-spacing\u0022\u003E\n      \u003Cdiv class=\u0022field__label h3 dash\u0022\u003ENature de l\u0026#039;\u00e9valuation\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003EEvaluation Terminale\u003C\/span\u003E\n                      \u003C\/div\u003E\n                  \u003C\/div\u003E\n      \u003C\/div\u003E\n  \u003C\/div\u003E\n\u003C\/div\u003E\n","settings":null}]