Understanding rewards by teaching a robot to navigate a maze
One of the biggest barriers to traditional machine learning is that most supervised and unsupervised machine learning algorithms need huge ...
Similar Articles (10 found)
🔍 66.2% similar
Deep Reinforcement Learning: Pong from Pixels
This is a long overdue blog post on Reinforcement Learning (RL). RL is hot! You may have noticed that co...
🔍 62.8% similar
Dynamic Programming in Reinforcement Learning
Our First Approach to Solving Reinforcement Learning Problems!
If you’re not familiar with the Bellman e...
🔍 60.2% similar
Building an AI Agent from Scratch with OpenAI and Postgres: A Complete Guide
In this comprehensive guide, I’ll walk you through the process of creatin...
🔍 55.9% similar
Introduction
I remember hearing “Learn Statistics to know what’s behind the algorithms” when I started studying Data Science. While all of that was fa...
🔍 54.3% similar
A Recipe for Training Neural Networks
Some few weeks ago I posted a tweet on “the most common neural net mistakes”, listing a few common gotchas relat...
🔍 54.0% similar
Designing agentic loops
30th September 2025
Coding agents like Anthropic’s Claude Code and OpenAI’s Codex CLI represent a genuine step change in how u...
🔍 53.8% similar
AlphaGo, in context
Update Oct 18, 2017: AlphaGo Zero was announced. This post refers to the previous version. 95% of it still applies.
I had a chance...
🔍 53.2% similar
Writing an LLM from scratch, part 22 -- finally training our LLM!
This post wraps up my notes on chapter 5 of Sebastian Raschka's book "Build a Large ...
🔍 52.7% similar
Vibe Coding as a Coding Veteran
From 8-bit Assembly to English-as-Code
By now, we’ve all heard about this “vibe coding” thing: you let an AI assistant...
🔍 52.7% similar
Shimmering Substance - Jackson Pollock
Think of this post as your field guide to a new way of building software.
Let me take you back to when this all...