1. Nan Values During Training 2. Policy does not get better

## Reinforcement Learning – Cheat Sheet

Policy gradient methods: Methods where we directly optimize the policy without the value function. Examples […]

## Y Combinator Notes – 3

How to found a startup? What matters most for a entrepreneurship? Domain expertise! Also, just […]

## Y Combinator Notes – 1

I only have some bullet points here without any category. References [1] https://www.youtube.com/watch?v=f4_14pZlJBs&list=PLQ-uHSnFig5MaafmEhFox7rO-b0RxQth-

## Y Combinator Notes – 2

How to know the growing markets? This turns out to be the easiest problem. Young […]

## Setting Up GPU Passthrough on Fedora with 2 GPUs

I have 2 GPUs. FIrst one is AMD, and I am adding a second one, […]

## NeRF – Nerual Radiance Field

Let’s start with these definitions:Zero-level set: is a mathematical function, e.g. is a level-set.Neural Implicit […]

## Fuzzing in Software Testing

Fuzzing in software testing means changing the program inputs so that you create different inputs […]

## Data Flow Analysis

Very Busy Expression Analysis Consider the following program: Note that a*b is used twice in […]

## Raspberry Pi UART Speed Test

After having some trouble with Raspberry Pi pyserial module, I started to think about some […]