Search

Patrick Saux
Patrick Saux
  • Home
  • Research
  • Teaching
  • Projects
  • Talks
  • Posts
  • Contact
  • Light Dark Automatic
  • Teaching
Reinforcement Learning (MAP/INF641, M2 Artificial Intelligence and Advanced Visual Computing, Ecole Polytechnique 2021-2022)
  • Deep Reinforcement Learning
  • Model-based
  • Planning
  • Contents
  1. Home
  2. Teaching
  3. Reinforcement Learning (MAP/INF641, M2 Artificial Intelligence and Advanced Visual Computing, Ecole Polytechnique 2021-2022)
  4. Planning

Planning

Planning in bandits: pure exploration, best arm identification. Planning in MDP: Monte Carlo Tree Search.

Practical session - Best arm identification

Practical session - MCTS on TicTacToe

Answers - Best arm identification

Answers - MCTS on TicTacToe

Previous
Model-based

Last updated on Feb 20, 2022

Published with Wowchemy — the free, open source website builder that empowers creators.

Cite
Copy Download