It’s been a whirlwind month filled with inspiring connections and exciting possibilities! I’m super excited about one role in particular under a Research Org – stay tuned for more life updates at the end of the month! 😄🤞🏻
Amidst all this, I found myself revisiting core ML and RL concepts last weekend. Surprisingly there weren’t many questions on RL, but I did read Sutton’s book, and I came across Bellman equations again, which is presented quite concisely. However, I felt compelled to fully flesh it out for quick reference next time. So, I figured I might as well make a post for my future self here, hoping it’ll also be helpful for others exploring this topic too.
I used some shorthand notation as I was quickly jotting it down, but this fleshed out derivation still captures all the key ideas.
