Methods › Reinforcement Learning › Q-Learning Networks › DQN

Deep Q-Network

DQN

519 papers tagged archive 2025-07-28

Introduced by Volodymyr Mnih et al. in Playing Atari with Deep Reinforcement Learning

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari Games case, they take in several frames of the game as an input and output state values for each action as an output.

It is usually used in conjunction with Experience Replay, for storing the episode steps in memory for off-policy learning, where samples are drawn from the replay memory at random. Additionally, the Q-Network is usually optimized towards a frozen target network that is periodically updated with the latest weights every k steps (where k is a hyperparameter). The latter makes training more stable by preventing short-term oscillations from a moving target. The former tackles autocorrelation that would occur from on-line learning, and having a replay memory makes the problem more like a supervised learning problem.

Image Source: here

PaperSource

Papers archive 2025-07-28

30 shown of 519, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 244 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Reinforcement Learning (RL)299
Reinforcement Learning265
reinforcement-learning260
Deep Reinforcement Learning217
Q-Learning116
Atari Games68
Decision Making38
Management21
Efficient Exploration17
Multi-agent Reinforcement Learning17
OpenAI Gym14
Scheduling14
Autonomous Driving13
Continuous Control10
Diversity9
Transfer Learning9
continuous-control9
Benchmarking8
EEG8
Imitation Learning8

Usage over time archive 2025-07-28

Papers per year tagged with DQN: 2013 to 2025, peak 92 92 0 2013: 1 paper 2013 2014: 1 paper 2014 2015: 8 papers 2015 2016: 9 papers 2016 2017: 24 papers 2017 2018: 40 papers 2018 2019: 52 papers 2019 2020: 72 papers 2020 2021: 92 papers 2021 2022: 53 papers 2022 2023: 70 papers 2023 2024: 65 papers 2024 2025: 32 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (519 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Q-Learning Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections