Methods › Reinforcement Learning › Off-Policy TD Control › Q-Learning

Q-Learning

introduced 1984 1,734 papers tagged archive 2025-07-28

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

Q-Learning is an off-policy temporal difference control algorithm:

Q(Sₜ, Aₜ) ←Q(Sₜ, Aₜ) + α[Rₜ₊₁ + γmaxₐQ(Sₜ₊₁, a) - Q(Sₜ, Aₜ)]

The learned action-value function Q directly approximates q_*, the optimal action-value function, independent of the policy being followed.

Source: Sutton and Barto, Reinforcement Learning, 2nd Edition

Papers archive 2025-07-28

30 shown of 1,734, 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 393 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
Q-Learning1,321
Reinforcement Learning (RL)898
reinforcement-learning783
Reinforcement Learning776
Deep Reinforcement Learning409
Decision Making134
Atari Games103
Multi-agent Reinforcement Learning100
Management74
Offline RL64
Scheduling60
Continuous Control46
OpenAI Gym45
continuous-control42
Sequential Decision Making34
Autonomous Driving33
Imitation Learning31
D4RL28
MuJoCo27
Autonomous Vehicles25

Usage over time archive 2025-07-28

Papers per year tagged with Q-Learning: 2009 to 2025, peak 269 269 0 2009: 1 paper 2009 2010: 1 paper 2011: 1 paper 2011 2012: 0 papers 2013: 6 papers 2013 2014: 5 papers 2015: 17 papers 2015 2016: 23 papers 2017: 64 papers 2017 2018: 110 papers 2019: 181 papers 2019 2020: 243 papers 2021: 269 papers 2021 2022: 188 papers 2023: 250 papers 2023 2024: 269 papers 2025: 106 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,734 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

Off-Policy TD Control

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