Watermarked Game Solving via Perturbed Regret Minimization

[2608.14977] Watermarked Game Solving via Perturbed Regret Minimization Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Science and Game Theory arXiv:2608.14977 (cs) [Submitted on 15 Aug 2026] Title: Watermarked Game Solving via Perturbed Regret Minimization Authors: Juho Kim , Tuomas Sandholm View a PDF of the paper titled Watermarked Game Solving via Perturbed Regret Minimization, by Juho Kim and Tuomas Sandholm View PDF HTML (experimental) Abstract: Many real-world interactions among self-interested parties can be modeled by game theory, and the rapid advancements in AI have raised concerns about the possible misuse---accidental or deliberate---of superhuman or human-level game-playing agents by bad actors. While AI watermarking has mainly been applied to LLM-generated texts, a recent line of work proposes developing watermarking techniques for agents in game-theoretic settings. However, existing watermarking techniques for game-theoretic agents are not readily applicable due to their limited scope or capabilities---they are tailored to perfect-information games and are thus inapplicable to richer game types. We propose a new approach to watermarking game-playing agents, which a) can be applied to imperfect-information settings; b) is directly integrated into the learning process itself; and c) incurs only a bounded cost in exploitability. For this purpose, we introduce perturbed regret minimization, which adds perturbations to the utilities prior to observation so as to encourage the learning algorithm to embed the watermark. Our experiments show that the watermark incurs only a small exploitability cost and can be detected within just a couple of hours of gameplay at human speed. Subjects: Computer Science and Game Theory (cs.GT) Cite as: arXiv:2608.14977 [cs.GT] (or arXiv:2608.14977v1 [cs.GT] for this version) https://doi.org/10.48550/arXiv.2608.14977 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Juho Kim [ view email ] [v1] Sat, 15 Aug 2026 01:59:54 UTC (100 KB) Full-text links: Access Paper: View a PDF of the paper titled Watermarked Game Solving via Perturbed Regret Minimization, by Juho Kim and Tuomas Sandholm View PDF HTML (experimental) TeX Source view license Current browse context: cs.GT < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark 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? ) 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? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Watermarked Game Solving via Perturbed Regret Minimization#612414
• Tandem Reinforcement Learning with Verifiable Rewards#319706
• PPAD-membership for problems with exact rational solutions: a general approach via convex optimization#1002122
• Optimizing Minimax Regret in Uncertain MDPs with Small Sets of Policies#423965
• Beyond Importance Sampling: Rejection-Gated Policy Optimization#19038