Reinforcement Learning

This talk is based on

• Tom M. Mitchell. Machine Learning. McGraw Hill. 1997. Chapter 13.
• and his slides.
• An excellent resource is Reinforcement Learning: An Introduction by Sutton and Barto (free!).

1. 1 Introduction*
   1. 1.1 TD-Gammon
   2. 1.2 Reinforcement Learning Problem*
   3. 1.3 The Learning Task
   4. 1.4 Value function
   5. 1.5 Example
2. 2 Q-Learning Motivation*
   1. 2.1 Q Function
   2. 2.2 Learning Q
   3. 2.3 Q-Learning Algorithm
   4. 2.4 Q-Learning Example
   5. 2.5 Q-Learning Convergence
   6. 2.6 How to Choose an Action
   7. 2.7 Variations
   8. 2.8 Nondeterministic Rewards and Actions
      1. 2.8.1 Nondeterministic Q-Learning
3. 3 Temporal Difference Learning
   1. 3.1 Temporal Difference
4. 4 Generalization from Examples

Entire Presentation with Notes (PDF)
Index on left

---

Copyright © 2004 José M. Vidal . All rights reserved.

19 August 2004, 03:11PM