From the archive · Thursday, 20 August 2026

The daily pick

One work a day, drawn from the 865 works in the library with a copy you can open — the same one for everybody, and a different one tomorrow.

Book1998

Reinforcement Learning: An Introduction

Richard Sutton & Andrew Barto

The standard text: builds the whole field from the bandit problem up to function approximation and policy gradients.

Level: Advanced
Access: Free
Length: —
Copy: link checked 17 Sept 2026
Filed under: Reinforcement Learning

Recently

Congressional Government: A Study in American PoliticsWoodrow Wilson19 Aug
Streptomycin Treatment of Pulmonary Tuberculosis: A Medical Research Council InvestigationMedical Research Council Streptomycin in Tuberculosis Trials Committee18 Aug
Hidden Technical Debt in Machine Learning SystemsSculley et al.17 Aug
Impossibility of Distributed Consensus with One Faulty ProcessMichael J. Fischer, Nancy A. Lynch & Michael S. Paterson16 Aug
Nicomachean EthicsAristotle15 Aug

The day picks the work, so this page is the same for every reader and every past day stays as it was. Nothing here is personalised, and nothing is recorded.