Hey, I'm Sebi. I'm writing my master's thesis on Reinforcement Learning and decided to document the whole mess publicly: progress, dead ends, concepts I'm trying to wrap my head around.
Partly to hold myself accountable, partly because Feynman was right:
"If you can't explain it simply, you don't understand it well enough."
Maybe it'll be useful to someone else too. We'll see.
Feel free to reach out at mail@sebastianwette.de