---
id: "2013-12-19-dqn-atari"
url: "https://postcutoff.com/e/2013-12-19-dqn-atari/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2013-12-19"
date_precision: day
category: research
importance: 4
confidence: high
status: [Confirmed]
sources: 2
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2013-12-19-dqn-atari/

# DeepMind's DQN learns to play Atari games from pixels

DeepMind combined deep convolutional networks with Q-learning (DQN) to learn Atari 2600 games directly from screen pixels; the 2015 Nature version reached human-level performance on many of 49 games.

## Key facts
- arXiv 1312.5602 'Playing Atari with Deep Reinforcement Learning' (December 2013)
- Nature paper 'Human-level control through deep reinforcement learning' (February 2015)
- Same architecture and hyperparameters across all games
- Google acquired DeepMind in early 2014

## What happened

DQN used experience replay and a target network to stabilize training of a deep Q-network on raw pixels and game score.

## Why it matters

Launched deep reinforcement learning as a field and put DeepMind on the path to AlphaGo.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Playing Atari with Deep Reinforcement Learning (arXiv)](https://arxiv.org/abs/1312.5602) (arxiv.org, paper)
2. [Human-level control through deep reinforcement learning (Nature, DOI)](https://doi.org/10.1038/nature14236) (doi.org, paper)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2016-03-15: [AlphaGo defeats Lee Sedol 4–1 at Go](https://postcutoff.com/e/2016-03-15-alphago-lee-sedol/index.md)