This chapter of Erdmann and Wildon’s Introduction to Lie Algebras covers various techniques of ideals and homomorphisms for Lie Algebras. In particular, it covers the quotient algebra (like in linear algebra) and the resulting homomorphism theorems (again like in lie algebra).
Today I covered lecture 9 in Berkeley’s deep rl course. This covered model based reinforcement learning, which tries to approximate the model. Note that model based planning covers the ways to optimize a policy given a model, so these two make a good couple.
This 6th chapter is really difficult. While I could digest most of the material covered, there was several challenging questions. It seemed like the reader was unprepared from some questions (like 13), as solutions I found online were either incomplete or required information in later chapters. I look forward to differentiation next chapter, but, for now, here’s my writeup:
Today I covered lecture 8 in Berkeley’s deep rl course. This covered model based planning, which optimizes a policy when the model is given.
I’ve started reading through Erdmann and Wildon’s Introduction to Lie Algebras as a good introduction to Lie Algebras bereft of any mention of manifolds. The first chapter doesn’t cover anything too complicated, just the basic definitions of Lie Algebras, so I’ll be looking forward to more complicated chapters. My writeup can be found below: