Rl Notes (to be updated)

I’m now the 4th year of undergrad and going to be a start for my graduate year this summer.

Last year, I dive into the learning of the Reinforcement Learning. From the beginning, just the shallow recognization, and now there will be a tough and complete studying period for me.

This page contains some notes during the studying. I try to combine the experienment coding and mathmatics, so I use the jupyter notebook to write.But the markdown can’t be supplied very well for the text transformed from jupyter. So I transform them into PDF to present. Forgive me that the layout may be little mess. If you have any idea of any more convinient ways, please contact me!

$$V(s_t) = \sum_a{Q(s,a)}$$

Notes list

• 01 Markov Decision Process and Dynamic Programming

• 02 Monte Carlo Method and Temporial Difference

• 01 Markov Decision Process and Dynamic Programming

• 02 Monte Carlo Method and Temporial Difference