---

Next: 6 Temporal Difference Learning

---

---

• 6 Temporal Difference Learning
  • 6.1 TD Prediction
  • 6.2 Advantages of TD Prediction Methods
  • 6.3 Optimality of TD(0)
  • 6.4 Sarsa: On-Policy TD Control
  • 6.5 Q-learning: Off-Policy TD Control
  • 6.6 Actor-Critic Methods (*)
  • 6.7 R-Learning for Undiscounted Continual Tasks (*)
  • 6.8 Games, After States, and other Special Cases
  • 6.9 Conclusions
  • 6.10 Historical and Bibliographical Remarks
• About this document ...

---

Richard Sutton
Fri May 30 13:53:05 EDT 1997