Skip to content

Latest commit

 

History

History
31 lines (24 loc) · 746 Bytes

File metadata and controls

31 lines (24 loc) · 746 Bytes

Reinforcement Learning

Textbook: Sutton and Barton: Reinforcement Learning An Inttroduction second edition

  • Markov decision process
  • Policy iteration and value iteration
  • Model-free prediction
  • Model-free control
  • On-Policy learning and off-policy learning
  • Connection to optimal control
  • Value function approximation
  • Deep Q Learning
  • Policy optimization
  • Imitation learning
  • Model-based Reinforcement Learning
  • Exploration and exploitation
  • Distributed computing and RL system design
  • Inverse RL and Real-world RL

Resources