// ♞ Reinforcement Learning

Deep Q-Network (DQN)

Approximates Q with a CNN to play Atari from pixels.

深度 Q 网络 DQN 2013 Intermediate core

IN PLAIN WORDS

Experience replay and a target network stabilize training, letting deep nets do RL and reach human level on many Atari games.

Used in: Baseline for deep RL

TIMELINE · prerequisites → this → what builds on it

1992 Q-Learning1998 Convolutional…2013 Deep Q-Network (D…2015 DDPG / TD3 (C…2016 Actor-Critic …2018 Soft Actor-Cr…2020 Conservative …2021 Decision Tran…

01Original paper

Playing Atari with Deep Reinforcement Learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, et al. · 2013

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Deep Q-Network (DQN)

Then you can learn

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Courses

huggingface.co ↗EN

Explainers

Lilian Weng：A (Long) Peek into Reinforcement Learning ↗EN

04Where the course teaches it

U33 Reinforcement Learning Basics MDPs, Q-learning, DQN, policy gradients, PPO and AlphaZero — the prerequisites for post-training and reasoning models. 14 h12 algorithms4 papers

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: dqn)