RL CS 2021

 Introduction to Reinforcement learning

1- [SLIDES] 
Introduction to RL, Short Introduction to Markov chains.

Markov framework for RL.

Markov decision processes
Bellman equations
Dynamic programming 

TP 

Markov + Bellman

Notebook

3- [SLIDES]

Bandits problems

TP

4- [SLIDES] 
Model free tabular problems.
Monte-Carlo and TD

5- [SLIDES]
Bigger state spaces: approximations of value functions
Policy gradient

Actor critic

BIBLIOGRAPHY:

Markov Chains: Gibbs Fields, Monte Carlo Simulation, and Queues (Texts in Applied Mathematics),
 by Pierre Bremaud (2001-02-01), Springer.

Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto

Second Edition, in progress MIT Press, Cambridge, MA, 2017

Dynamic programing and optimal control, D. Bertsekas,

SA, 2012