HN Hall of Fame Weekly email

Deep Reinforcement Learning: Pong from Pixels

karpathy.github.io Essays & writing Essays & articles AI & data Candidate
Screenshot of karpathy.github.io captured 2026-07-20
Page preview · captured 2026-07-20

Resurfaced independently across 5 calendar years, with breakout response in 2 of them.

submissions
5
submitters
5
observed span
2016–2025
peak thread · 13 comments
189 pts
latest 20+ return · 2025-02-06
111 pts

Submission timeline

2007–2026

One slot for every year since HN launched. Height is that year's peak points; orange marks a 100+ point or 50+ comment breakout. Select a bar to open its strongest thread.

First comments on top threads

HN comment order

Fascinating. Many years ago, when I wanted to become a programmer and I didn't know anything about code, I used to fantasize and be amazed by programs. Code was like dark magic. This is how I feel today about machine learning. Neural networks, liquid state machines. It's wonderful voodoo to my eyes. I hope one day I get to work in that field, it seems so useful for solving big world problems. I have notice a definite rise in articles…

keyle·189-point thread·

I sometimes reminisce about the 2010-2020 deep learning and reinforcement learning etc era, as a student I did some projects in that domain back then and it felt very approachable and relatively easy to get into it compared to how I (most likely subjectively) see it today as a developer (in a different field). I remember I doing a project in my second bachelor semester, where I generated random 64x64 images of a simple maze with a start and finish…

c-fe·111-point thread·

Discussed at the time: https://news.ycombinator.com/item?id=11811118

dang·57-point thread·

The first top-level comment from each of the four biggest threads, in HN’s own order. Excerpts are shortened; open a comment for full context.

Breakout years
2

100+ points or 50+ comments

Total points
362

reference only — not used in Hall rules or ranking

Total comments
20

reference only — not used in Hall rules or ranking

Every submission

DateTitle as submittedByPointsComments
2016-05-31Deep Reinforcement Learning: Pong from PixelsFirst breakout · Best threadSmerity18913
2017-08-28Deep Reinforcement Learning: Pong from Pixelssigna1140
2018-08-18Deep Reinforcement Learning: Pong from Pixels (2016)sonabinu571
2022-12-31Deep Reinforcement Learning: Pong from Pixels (2016)gone3510
2025-02-06Deep Reinforcement Learning: Pong from Pixels (2016)Latest 20+ point returnAnon841116