Online Learning with Off-Policy Feedback
We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback.
germano.dev
undefined
Latest posts
Server-Sent Events: the alternative to WebSockets you should be using
WebSockets are the most used technology for real-time web apps. However, Server Sent Events (SSE) are a simpler alternative that is often superior.
On the security of WhatsApp and Telegram
Many people hold the firm belief that WhatsApp is more secure and privacy-wise better than Telegram. Is that really the case?
A Reinforcement Learning Riddle
I proved 1=0 starting from the formula for the on-policy distribution in episodic tasks. Obviously there is some mistake, can you spot it? 🤔.
Conquer your dotfiles with VCSH and MR
Are you tired of wasting time setting up your dotfiles every time you change laptop? Here I will describe a simple method based on vcsh and later show how you can make it more customizable and modular, thanks to myrepos.
How to make Netlify CMS image paths work on Gridsome
Gridsome and NetlifyCMS are fantastic software projects, which allow you to respectively create a blazingly fast static website and manage your content from a beautiful UI. However they disagree on how to handle file paths of images or blog post covers.
Be angry with yourself, not Apple
Why you have no right to complain about the new MacBook
Fuckpyjails Writeup
Remote Code Execution As A Service — 9447 CTF