Methods › Reinforcement Learning › Replay Memory › Experience Replay

Experience Replay

introduced 1993 865 papers tagged archive 2025-07-28

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

Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, eₜ = (sₜ, aₜ, rₜ, sₜ₊₁) in a data-set D = e₁, ⋯, e_N , pooled over many episodes into a replay memory. We then usually sample the memory randomly for a minibatch of experience, and use this to learn off-policy, as with Deep Q-Networks. This tackles the problem of autocorrelation leading to unstable training, by making the problem more like a supervised learning problem.

Image Credit: Hands-On Reinforcement Learning with Python, Sudharsan Ravichandiran

Papers archive 2025-07-28

30 shown of 865, 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 289 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)440
reinforcement-learning375
Reinforcement Learning371
Deep Reinforcement Learning296
Continuous Control99
Q-Learning94
continuous-control93
Continual Learning90
MuJoCo54
Decision Making49
OpenAI Gym43
Multi-agent Reinforcement Learning42
Atari Games34
Management25
Autonomous Driving22
Imitation Learning21
Incremental Learning21
Scheduling20
Diversity17
Multi-Goal Reinforcement Learning17

Usage over time archive 2025-07-28

Papers per year tagged with Experience Replay: 2013 to 2025, peak 145 145 0 2013: 1 paper 2013 2014: 0 papers 2014 2015: 3 papers 2015 2016: 5 papers 2016 2017: 17 papers 2017 2018: 57 papers 2018 2019: 86 papers 2019 2020: 129 papers 2020 2021: 145 papers 2021 2022: 113 papers 2022 2023: 134 papers 2023 2024: 117 papers 2024 2025: 58 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (865 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

Replay Memory

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