Methods › Reinforcement Learning › Randomized Value Functions › Noisy Linear Layer

Noisy Linear Layer

11 papers tagged archive 2025-07-28

Introduced by Meire Fortunato et al. in Noisy Networks for Exploration

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

A Noisy Linear Layer is a linear layer with parametric noise added to the weights. This induced stochasticity can be used in reinforcement learning networks for the agent's policy to aid efficient exploration. The parameters of the noise are learned with gradient descent along with any other remaining network weights. Factorized Gaussian noise is the type of noise usually employed.

The noisy linear layer takes the form:

y = (b + Wx) + (b_(noisy)⊙ϵᵇ+(W_(noisy)⊙ϵʷ)x)

where ϵᵇ and ϵʷ are random variables.

PaperSource

Papers archive 2025-07-28

11 shown of 11, 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

13 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)9
Deep Reinforcement Learning8
reinforcement-learning6
Reinforcement Learning5
Atari Games3
Q-Learning3
Efficient Exploration2
Computational Efficiency1
Decision Making1
Diversity1
Ensemble Learning1
Game of Go1
Montezuma's Revenge1

Usage over time archive 2025-07-28

Papers per year tagged with Noisy Linear Layer: 2017 to 2024, peak 3 3 0 2017: 2 papers 2017 2018: 0 papers 2018 2019: 1 paper 2019 2020: 3 papers 2020 2021: 2 papers 2021 2022: 2 papers 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (11 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

Randomized Value Functions

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