The Unscalable
Subscribe
Sign in
Home
AI/ML Tutorials
Human & Tech
LLM & "AGI"
Archive
About
ai-ml-tutorial
The Beauty of Reinforcement Learning (3) - PPO Demystified
Including analogies that give you a vivid idea of how PPO works, and all the maths that you need to know PPO and its history thoroughly, end to end.
Aug 11
•
Forest
5
The Beauty of Reinforcement Learning (2) - Reinforce with Baseline, A2C & GAE
Reducing the variance of policy gradient algorithms, from REINFORCE with baseline to A2C, to GAE that gracefully unifies them all.
Aug 2
•
Forest
The Beauty of Reinforcement Learning (1) - Intro of Policy Based Methods
Reinforcement learning is powerful, beautiful and approachable - an intuitive yet in-depth introduction to reinforcement learning, including the what…
Jul 26
•
Forest
5
Four Simple but Profound Lessons I Learned about ML and AI
The first two lessons are historically influential thesis that have shaped today’s AI/ML research and industry, while the last two lessons tell the flip…
Feb 17
•
Forest
1
From Solomonoff Induction to the Relationship between World, Human and Machine (Part 2)
A thorough illustration of the beauty of Solomonoff induction, its optimality, the reason why such an optimal prediction machine can’t be built to…
Sep 4, 2024
•
Forest
From Solomonoff Induction to the Relationship between World, Human and Machine (Part 1)
In a series of posts, I will introduce Solomonoff's theory of inductive inference, which is an idealized model for universal prediction and deep dive…
Jun 23, 2024
•
Forest
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
