Metraipolis › archive › dc_082160af3bad

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games — arXiv:2611.02875

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02875
License (as archived)
CC0-1.0
Archived
2026-11-03T18:09:41.386Z
SHA-256 of the archived text
b4073b77a2a0b27fbd5e1f570c8517d531e0fca7cdb24a6a23d1ca34f89d6dc1
Stable URL of this page
https://metraipolis.com/documento/dc_082160af3bad

How to cite

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games — arXiv:2611.02875 — arXiv (en), https://arxiv.org/abs/2611.02875 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_082160af3bad (Metraipolis archive dc_082160af3bad, sha256 b4073b77a2a0b27fbd5e1f570c8517d531e0fca7cdb24a6a23d1ca34f89d6dc1)
BibTeX
@misc{dc082160af3bad,
  title = {AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games — arXiv:2611.02875},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02875},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_082160af3bad; sha256 b4073b77a2a0b27fbd5e1f570c8517d531e0fca7cdb24a6a23d1ca34f89d6dc1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02875. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we consider mixed-motive games (MMGs) which model various real-world multi-agent scenarios where self-interested agents must both cooperate and compete. We identify an issue with existing gifting methods, where agents become overly dependent on incoming gifts and fail to learn reward-yielding behaviors, a phenomenon we call gift over-reliance. To address this, we propose a refusal-augmented gifting framework that balances cooperation and competition in MMGs. Our approach introduces an adaptive refusal mechanism that allows agents to selectively reject a portion of received gifts from their policy-update signals, thereby mitigating gift over-reliance and preventing the agents from being exploited by other agents. This mechanism is gifting-method-agnostic, serving as a plug-in for existing schemes while enabling decentralized learning. We demonstrate that across diverse MMG environments and gifting schemes, our mechanism consistently reduces gift over-reliance and prevents lock-in to sacrificing policies, improving $\alpha$-fairness as a result, without necessitating major changes to existing training pipelines.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02875 — 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 2026-11-03T18:09:37.679Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).