Methods › Reinforcement Learning › Q-Learning Networks › Dueling Network

Dueling Network

23 papers tagged archive 2025-07-28

Introduced by Ziyu Wang et al. in Dueling Network Architectures for Deep Reinforcement Learning

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

A Dueling Network is a type of Q-Network that has two streams to separately estimate (scalar) state-value and the advantages for each action. Both streams share a common convolutional feature learning module. The two streams are combined via a special aggregating layer to produce an estimate of the state-action value function Q as shown in the figure to the right.

The last module uses the following mapping:

Q(s, a, θ, α, β) =V(s, θ, β) + (A(s, a, θ, α) - 1/(|𝒜|)∑_(a′)A(s, a′; θ, α))

This formulation is chosen for identifiability so that the advantage function has zero advantage for the chosen action, but instead of a maximum we use an average operator to increase the stability of the optimization.

PaperSource

Papers archive 2025-07-28

23 shown of 23, 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 25 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)18
Deep Reinforcement Learning17
Reinforcement Learning15
reinforcement-learning15
Atari Games7
Q-Learning5
Decision Making3
Efficient Exploration2
Multi-agent Reinforcement Learning2
OpenAI Gym2
Starcraft2
Computational Efficiency1
Continuous Control1
Distributional Reinforcement Learning1
Diversity1
Ensemble Learning1
Game of Go1
General Reinforcement Learning1
Management1
Montezuma's Revenge1

Usage over time archive 2025-07-28

Papers per year tagged with Dueling Network: 2015 to 2024, peak 6 6 0 2015: 1 paper 2015 2016: 2 papers 2016 2017: 2 papers 2017 2018: 2 papers 2018 2019: 2 papers 2019 2020: 6 papers 2020 2021: 3 papers 2021 2022: 2 papers 2022 2023: 2 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (23 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