[2605.16315] A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning
[Submitted on 4 May 2026]
Title:A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning
View a PDF of the paper titled A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning, by Arahan Kujur
View PDF HTML (experimental)
Abstract:We show that a threshold in decision capacity determines whether self-play reinforcement learning agents collapse under asymmetric rule perturbations. Across poker variants, matrix games, a dice game, and multiple learning algorithms, eliminating all positive-reach contingent decisions causes rapid convergence to a deterministic exploitation attractor, a fixed point at near-maximal loss. Preserving even a single positive-reach contingent decision point prevents this collapse. A frozen baseline and fixed-opponent control confirm that the mechanism is co-adaptation under constraint, not the perturbation itself. The phenomenon is timing-invariant, fully reversible upon action restoration, and intensifies under function approximation. These results establish a sharp threshold at zero reach-weighted contingent action capacity, with severity scaling continuously via reach-weighted capacity in the tested domains.
Comments: 18 pages, 7 figures
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
MSC classes: 91A05, 91A26, 68T05, 68T42
ACM classes: I.2.6; I.2.8; F.2.2
Cite as: arXiv:2605.16315 [cs.LG]
(or arXiv:2605.16315v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.16315
arXiv-issued DOI via DataCite
Submission history
From: Arahan Kujur [view email] [v1] Mon, 4 May 2026 19:09:14 UTC (1,022 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning, by Arahan Kujur
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
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, Media
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
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
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?)
Author
Venue
Institution
Topic
About arXivLabs
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.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)