Introduction to RL in Depth

goal

get deeper into the concepts. learn new math that are usfull for RL

overview

value iteration

policy iterration

liptishtness

contraction mapping

DDPG

natural gradient

policy gradient

kl

TRPO theory

SAC theory

conceteration bound

hofdding

regret bound

ucb

notaion

here is a the notation we will use thgoht this part:

prequestions

you may need to know the follwing concepts two better undestad this part: