Metraipolis › archive › dc_fa76fbbc4160

Watermarked Game Solving via Perturbed Regret Minimization — arXiv:2608.14977

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.14977
License (as archived): CC0-1.0
Archived: 2026-10-18T19:08:01.370Z
SHA-256 of the archived text: 189309bd7e69569015f4d216e1da15da020d0934634e947cefa9e0a9dace432b
Stable URL of this page: https://metraipolis.com/documento/dc_fa76fbbc4160

How to cite

Watermarked Game Solving via Perturbed Regret Minimization — arXiv:2608.14977 — arXiv (en), https://arxiv.org/abs/2608.14977 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa76fbbc4160 (Metraipolis archive dc_fa76fbbc4160, sha256 189309bd7e69569015f4d216e1da15da020d0934634e947cefa9e0a9dace432b)

BibTeX

@misc{dcfa76fbbc4160,
  title = {Watermarked Game Solving via Perturbed Regret Minimization — arXiv:2608.14977},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14977},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa76fbbc4160; sha256 189309bd7e69569015f4d216e1da15da020d0934634e947cefa9e0a9dace432b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14977. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-08-18 in cs.GT).
Categorie arXiv: Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2608.14977 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T18:12:50.739Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).