1 / 22

CHAPTER 10

CHAPTER 10. Reinforcement Learning Utility Theory. QUESTION????. Recap: MDPs. Reinforcement Learning. Example: Animal Learning. RL studied experimentally for more than 60 years in psychology  Rewards: food, pain, hunger, drugs, etc.  Mechanisms and sophistication debated

Download Presentation

CHAPTER 10

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CHAPTER 10 Reinforcement LearningUtility Theory

  2. QUESTION????

  3. Recap: MDPs

  4. Reinforcement Learning

  5. Example: Animal Learning • RL studied experimentally for more than 60 years in psychology  Rewards: food, pain, hunger, drugs, etc.  Mechanisms and sophistication debated • Example: foraging  Bees learn near-optimal foraging plan in field of artificial flowers with controlled nectar supplies  Bees have a direct neural connection from nectar intake measurement to motor planning area

  6. Example: Backgammon

  7. Passive Learning

  8. Example: Direct Estimation

  9. Model-Based Learning • Idea:  Learn the model empirically (rather than values) •  Solve the MDP as if the learned model were correct • Empirical model learning  Simplest case:  Count outcomes for each s,a  Normalize to give estimate of T(s,a,s’)  Discover R(s) the first time we enter s • More complex learners are possible (e.g. if we know that all squares have related action outcomes “stationary noise”)

  10. Example: Model-Based Learning

  11. Model-Free Learning

  12. (Greedy) Active Learning • In general, want to learn the optimal policy Idea: • Learn an initial model of the environment: • Solve for the optimal policy for this model (value or policy iteration) • Refine model through experience and repeat

  13. Example: Greedy Active Learning

  14. Q-Functions

  15. Learning Q-Functions: MDPs

  16. Q-Learning

  17. Exploration / Exploitation

  18. Exploration Functions

  19. Function Approximation • Problem: too slow to learn each state’s utility one by one • Solution: what we learn about one state should generalize to similar states • Very much like supervised learning • If states are treated entirely independently, we can only learn on very small state spaces

  20. Discretization

  21. Linear Value Functions

  22. TD Updates for Linear Values

More Related