[{"command":"insert","method":null,"selector":".course-modal-ajax-placeholder-967503","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 AI\n\u003C\/h2\u003E\n                  \u003Cdiv class=\u0022field-spacing\u0022\u003E\n        \u003Cdiv class=\u0022field__label h3 dash\u0022\u003EECTS :\n          3\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\u003E12\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003EPractical study :\u003C\/span\u003E\n                                      \u003Cspan\u003E8\u003C\/span\u003E\n                      \u003C\/div\u003E\n                                \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                          \u003Cspan class=\u0022field__label h4 mt-5 \u0022\u003EDirected study:\u003C\/span\u003E\n                                      \u003Cspan\u003E6\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\u003EProgramme \/ plan \/ contenus\u003C\/div\u003E\n                        \u003Cdiv class=\u0022mt-5 text-justify\u0022\u003E\n                                      \u003Cspan\u003E\u003Cp\u003E1. Introduction to Reinforcement Learning (RL)\u003C\/p\u003E\n\u003Cp\u003EDefinition and motivation\u003C\/p\u003E\n\u003Cp\u003ERL framework: agent, environment, states, actions, rewards\u003C\/p\u003E\n\u003Cp\u003EMarkov Decision Processes (MDP) and Bellman equations\u003C\/p\u003E\n\u003Cp\u003EExploration vs. exploitation\u003C\/p\u003E\n\u003Cp\u003E2. Classical RL Methods\u003C\/p\u003E\n\u003Cp\u003EDynamic Programming: policy evaluation, policy iteration, value iteration\u003C\/p\u003E\n\u003Cp\u003EMonte Carlo methods\u003C\/p\u003E\n\u003Cp\u003ETemporal Difference learning: SARSA, Q-Learning\u003C\/p\u003E\n\u003Cp\u003E3. Policy Gradient and Actor\u2013Critic Methods\u003C\/p\u003E\n\u003Cp\u003EValue-based vs. policy-based methods\u003C\/p\u003E\n\u003Cp\u003EREINFORCE algorithm and stochastic policy gradients\u003C\/p\u003E\n\u003Cp\u003EActor\u2013Critic architecture and advantage estimation (A2C, A3C)\u003C\/p\u003E\n\u003Cp\u003E4. Deep Reinforcement Learning (Deep RL)\u003C\/p\u003E\n\u003Cp\u003EFunction approximation using neural networks\u003C\/p\u003E\n\u003Cp\u003EDeep Q-Network (DQN) and its extensions (Double DQN, Dueling DQN, PER)\u003C\/p\u003E\n\u003Cp\u003EDeep policy optimization: PPO, TRPO, DDPG, TD3, SAC\u003C\/p\u003E\n\u003Cp\u003ETraining stability, reward shaping, and exploration strategies\u003C\/p\u003E\n\u003Cp\u003E5. Model-Based and Hierarchical RL\u003C\/p\u003E\n\u003Cp\u003EModel-based planning: Dyna-Q, world models\u003C\/p\u003E\n\u003Cp\u003EHierarchical RL: options framework, sub-policy learning\u003C\/p\u003E\n\u003Cp\u003EMeta-learning in RL\u003C\/p\u003E\n\u003Cp\u003E6. Multi-Agent Reinforcement Learning\u003C\/p\u003E\n\u003Cp\u003ECooperative and competitive settings\u003C\/p\u003E\n\u003Cp\u003ECommunication and coordination among agents\u003C\/p\u003E\n\u003Cp\u003EApplications to swarm robotics and game environments\u003C\/p\u003E\n\u003Cp\u003E7. Applications of Deep RL\u003C\/p\u003E\n\u003Cp\u003ERobotics control and motion planning\u003C\/p\u003E\n\u003Cp\u003EAutonomous driving and drone navigation\u003C\/p\u003E\n\u003Cp\u003EGame playing (Atari, Go, StarCraft)\u003C\/p\u003E\n\u003Cp\u003EDecision making in finance and resource optimization\u003C\/p\u003E\n\u003Cp\u003E8. Recent Trends and Advanced Topics\u003C\/p\u003E\n\u003Cp\u003EOffline RL and imitation learning\u003C\/p\u003E\n\u003Cp\u003ESafe and explainable RL\u003C\/p\u003E\n\u003Cp\u003ECurriculum learning and lifelong RL\u003C\/p\u003E\n\u003Cp\u003EFoundation models for control (e.g., Gato, RT-2, Diffusion Policies)\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 Continue non Int\u00e9grale\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}]