A new interactive publication

Machine learning,
made tangible.

Visual essays and small experiments for understanding what models are really doing — one difficult idea at a time.

Recently planted. New articles are published deliberately.

The library

All articles

5 articles

Sample-based reinforcement learningLatest

A Sample-Based View of Reinforcement Learning

Follow experience through an MDP, then compare how reinforcement learning algorithms collect samples, update learned quantities, and represent what they learn.

ACF and PACF

How the Past Echoes: Understanding ACF and PACF

Begin with ordinary correlation, shift a series through time, and see how lagged relationships become an autocorrelation function.

Reward hacking

Reward Hacking in Reinforcement Learning

Three small MDPs show how an agent can exploit a missing restriction, manipulate a measurement process, or optimize an incomplete objective.

Regression trees

How decision trees learn to predict numbers

Keep the same propose–judge–repeat procedure, replace class impurity with squared error, and let each leaf predict its mean.

Decision trees

How to invent the decision tree algorithm from scratch

Build a classification tree by hand from ten seeds, then automate your own judgment with midpoint thresholds and the Gini score.