Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Plan RL #45

Open
MohamedBsh opened this issue Apr 24, 2022 · 2 comments
Open

Plan RL #45

MohamedBsh opened this issue Apr 24, 2022 · 2 comments

Comments

@MohamedBsh
Copy link
Collaborator

MohamedBsh commented Apr 24, 2022

plan proposé par @AntoninLagarrigue (Discord : Zinzolin)

Module I: Introduction
Notions fondamentales

  1. Introduction
  2. Bandit Multi-armes
  3. Processus de décision markoviens
  4. Programmation Dynamique

Module II: Notions générales
Les algos de RL

  1. Monte Carlo
  2. TD Learning
  3. Conclusion sur les méthodes tabulaires

Module III: Spécialisé ++
Deep Reinforcement Learning
1. Deep Q-Learning
2. Policy Gradient
3. Actor Critic

@MHaurel
Copy link
Collaborator

MHaurel commented Aug 21, 2022

Plan proposé par @MHaurel (Discord: Maxxx)

Notions de base (Introduction)
Fondations du RL

  • Brève introduction
  • Bandit multi-armes
  • Processus de Décision Markoviens
  • Fonctions basées sur Valeurs et Politiques
  • Dynamic Programming

Notions élémentaires
Algos de RL

  • Monte-Carlo
  • Temporal Difference Learning
  • Q-Learning: (Théorie & Exemple)
  • SARSA
  • MinMax
  • OpenAI Gym : Overview

Notions avancées
Approfondissement du RL

  • Deep Q-Learning (Théorie & Exemple)
  • Actor Critic
  • Algorithmes évolutionnistes

@MHaurel
Copy link
Collaborator

MHaurel commented Aug 21, 2022

Voici ma proposition pour le nouveau plan de Reinforcement Learning

@MHaurel MHaurel self-assigned this Aug 25, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Development

No branches or pull requests

3 participants