Neural Foundations · 2015

Human-level Control through Deep RL (DQN)

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

Introduced the Deep Q-Network (DQN), which combined Q-learning with a convolutional neural network to learn control policies directly from raw pixels, reaching human-level play across many Atari games with one architecture.

Editorial record

Plain-language summary

Mnih and colleagues trained a network to estimate action values from screen images, using two stabilizing tricks: an experience replay buffer that reuses and decorrelates past transitions, and a periodically updated target network. The same model and hyperparameters learned to play 49 Atari games from pixels and reward alone. It showed that deep networks could serve as reliable function approximators in reinforcement learning, launching the deep RL field.

Knowledge graph

Relationships

Descendants

CombinesEvidence: Direct
Q-learning
DQN combines Q-learning with deep CNNs
A-033

Source record

Provenance

Record ID: A-033
Record created: 2026-07-13
Last reviewed: 2026-07-14
Record version: 2

https://www.nature.com/articles/nature14236

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.