Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
arXiv:2607.19397 (cs)
[Submitted on 4 Jul 2026]
Title:Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning
View a PDF of the paper titled Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning, by Adrian Ly and 4 other authors
View PDF
HTML (experimental)
Abstract:Deep Q-networks use target networks to stabilise bootstrapped value learning, but the standard hard copy update also introduces a tradeoff. Holding the target network fixed, improves short term stability, yet each hard update abruptly replaces the target parameters with the newest online network and discards recent parameter history. This can produce sudden changes in the bootstrap target and may remove value function structure that remains useful later in training. This paper introduces Memory Merge DQN, a target network update mechanism that maintains a short memory of recent historical online network copies and constructs the target network by merging network parameters based on the Q-value sensitivity rather than copying only the newest online network. Memory Merge gives greater influence to parameters that remain locally important for current Q-value behaviour, while using a recency prior to keep the merged target close to the latest online parameters. The method is inspired by Fisher Weight Model Merging, but uses Q-value sensitivity rather than Fisher information as the weighting signal. This paper evaluates Memory Merge DQN on Atari environments against DQN, Averaged DQN, DQN with layer normalisation, and PQN (with gradient clipping). The results show that Memory Merge DQN is highly competitive and it achieves the largest number of first place final performance results among the evaluated methods, beats DQN, Averaged DQN, and PQN (with gradient clipping), and produces substantial gains in several games where preserving useful value-function parameters appears beneficial. These findings suggest that selectively merging recent parameter weights and history can improve the stability and final performance of DQN agents, and that target network design is an important mechanism for preserving useful value function structure during long horizon value learning.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.19397 [cs.LG] |
| (or arXiv:2607.19397v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.19397
arXiv-issued DOI via DataCite (pending registration)
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled Memory Merge DQN: Sensitivity Weighted Target Updates for Stable Value Learning, by Adrian Ly and 4 other authors
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender
(What is IArxiv?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Learning Discrete Riemannian Metrics for Physical Fields with Cochain-Frame Equivarianc
Aug 18
-
Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)
Aug 18
-
Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
Aug 18
-
Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation
Aug 18
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.