Reinforcement Learning (CentraleSupelec M2 2020-2021)

Overview

Optimal control, stochastic and structured bandits, model-based MDP, planning, deep reinforcement learning.

Teaching assistant for practical sessions.

• 1. MDP

  Introduction to Markov Decision Processes, Bellman operators and control.

• 2. Bandits

  Introduction to stochastic and structured bandits.

• 3. Planning

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

• 4. Deep Reinforcement Learning

  Deep RL, DQN.