Next:
Introduction
Reinforcement Learning - Final Project
Adi Akavia
Introduction
Notations
The Parallel Sampling Model
The Learning Algorithms
Direct Algorithm - Phased-Q-Learning
Indirect Algorithm
The Main Theorem - Bound on the Number of Samples
My Results
Proof for Phased Q-Learning
Notations
Bounding
Putting It All Together
Finding the Constants
m
D
and
l
D
Proof for The Indirect Algorithm
Notations
Bounding the Number of Calls to
PS
(
M
)
Conclusions
About this document ...
Yishay Mansour
2000-05-30
