Reinforcement Learning

Notes from:

• Understanding Deep Learning

Basics

• RL Basics

• Markov Process

• Policy

• Value Function

• Bellman Equations

• Tabular Reinforcement Learning

  • Dynamic Programming RL
  • Monte Carlo Methods
  • On-Policy vs. Off-Policy
  • Temporal Difference Methods
    • SARSA
    • Q-Learning

• Fitted Q-Learning

  • Deep Q-Networks
  • Double Q-Learning

• Policy Gradient Methods

  • REINFORCE

• Actor-Critic Methods

• Offline Reinforcement Learning