Metraipolis › archive › dc_3c1941bf32d3

Cooperation Without Shared Rewards via Reciprocal Q-Augmentation — arXiv:2610.24793

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.24793
License (as archived): CC0-1.0
Archived: 2026-10-20T11:41:02.251Z
SHA-256 of the archived text: 1165d65f81da23227bdf9937f48125326016e0f8eca93ff6a3eeef820224d8e1
Stable URL of this page: https://metraipolis.com/documento/dc_3c1941bf32d3

How to cite

Cooperation Without Shared Rewards via Reciprocal Q-Augmentation — arXiv:2610.24793 — arXiv (en), https://arxiv.org/abs/2610.24793 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c1941bf32d3 (Metraipolis archive dc_3c1941bf32d3, sha256 1165d65f81da23227bdf9937f48125326016e0f8eca93ff6a3eeef820224d8e1)

BibTeX

@misc{dc3c1941bf32d3,
  title = {Cooperation Without Shared Rewards via Reciprocal Q-Augmentation — arXiv:2610.24793},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.24793},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c1941bf32d3; sha256 1165d65f81da23227bdf9937f48125326016e0f8eca93ff6a3eeef820224d8e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.24793. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Achieving high social welfare requires sustained cooperation, while a single defection can drive agents toward a welfare suboptimal Nash equilibrium. Moreover, assuming access to other agents' rewards or internal states is often unrealistic and implicitly introduces additional cooperation into the setting. To address this issue, we introduce \textit{Reciprocal Q-Augmentation} (RQA), a method that uses a latent-variable opponent model to augment the Q-function with estimates of how one's actions affects other agents. RQA allows agents to learn both cooperative and defective policies using only their own Q-function. We show that, in social dilemmas, agents that all follow the cooperative policy of RQA learn to cooperate faster and reach higher levels of cooperation than fully cooperative algorithms. Moreover, a single RQA agent that switches appropriately between its cooperative and defecting policies can induce cooperation in agents trained with standard RL algorithms, which would otherwise end up defecting. We evaluate our approach on the Iterated Prisoner's Dilemma, Iterated Traveler's Dilemma, Iterated Stag Hunt, and \texttt{CleanUp-Lite}. Our experiments show that the algorithms implementing RQA outperforms fully cooperative methods with shared rewards and enables cooperation with algorithms that otherwise fail to reach high social welfare.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.24793 — 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 2026-10-20T11:41:00.023Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).