Table of Contents
Understanding Reinforcement Learning Without Really Trying
We want to learn what to do given where you are…
Markov Decision Process (MDP)
More Formally...
The Holy Grail of RL
Why Use This Crazy Scheme? (Real World Examples)
That's Great! Why Haven't We Discovered The Meaning of Life?
Flavors of Reinforcement Learning
Are There Convergence Proofs?
|
Author: Kevin Dixon
Email: krd@cs.cmu.edu
|