The impossible chessboard puzzle made possible
One of my favorite creators on youtube on the channel 3Blue1Brown posted a video on the Impossible Chessboard Puzzle, (a link is included below). Here I will...
Posts by Category
math
Intro to Variational Inference - Part 1
This is the first of an N part series (I don’t know N yet), where I take a deep dive into a class of techniques commonly known as variational inference. This...
Intro to Variational Inference - Part 2
In this part of the intro to variational inference (VI) series, we explore maximizing an intractable likelihood function \(p(X)\) using the VI framework. Fi...
reinforcement-learning
Trust Region Policy Optimization: Practical Algorithm
In the last post on TRPO, we proved the Monotonic Improvement Guarantee Theorem (MIGT) and derived a lower bound to the true objective \(\eta(\tilde{\pi})\):
Trust Region Policy Optimization: Monotonic Improvement
In this post we’ll be talking about the famed Trust Region Policy Optimization (TRPO) paper. It’s a relatively dense paper filled with a ton of interesting ...